diff --git a/category/all/index.html b/category/all/index.html index 9ed37205..293d1f14 100644 --- a/category/all/index.html +++ b/category/all/index.html @@ -2,4 +2,4 @@ function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); - gtag('config', 'G-4ZPP8W4RNN');Skip to content

Category — All

\ No newline at end of file + gtag('config', 'G-4ZPP8W4RNN');Skip to content

Category — All

\ No newline at end of file diff --git a/index.html b/index.html index 81d931f2..f1151c82 100644 --- a/index.html +++ b/index.html @@ -2,4 +2,4 @@ function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); - gtag('config', 'G-4ZPP8W4RNN');Skip to content

Privacy Preserving Systems Lab

We at the PPS Lab build, investigate, and research software systems for data privacy and data security. Our mission is to develop technologies that enable applications to safely and securely interact with users data while preserving individual's privacy and make it easy for developers to build and develop privacy preserving applications.

Our members are affiliated with the Systems Group and the Applied Cryptography Group at ETH Zurich CS Department.

Projects

Secure and Robust Collaborative Learning thumbnail

Secure and Robust Collaborative Learning

End-to-End Designs for Data Privacy thumbnail

End-to-End Designs for Data Privacy

Accessible Privacy Preserving Computation thumbnail

Accessible Privacy Preserving Computation

Privacy Preserving Stream Analytics at Scale thumbnail

Privacy Preserving Stream Analytics at Scale

News

Arc is accepted at USENIX Security 2024!

Cohere is accepted at IEEE S&P (Oakland) 2024!

We received the best talk award at HotPETs for our work on "Bridging the Gap between Privacy Incidents and PETs"!

Alex successfully defended his PhD thesis last week. Congratulations, Dr. Alex! Photo.

RoFL is accepted at IEEE S&P (Oakland) 2023!

Chris gave talks about Verifiable Fully Homomorphic Encryption at UC Berkeley Sec. Seminar, Stanford Sec. Seminar, Intel Labs, UCSD (invited guest lecture), and the FHE.org conference. Check the talk here.

We received the Google Research Award!

This award will foster a new collaboration with Google that aims to bring efficient and scheme-agnostic FHE support to the TensorFlow framework.

HECO is accepted at USENIX Security 2023!

Congratulations to Lukas Burkhalter, who successfully defended his Ph.D. thesis this week! Photo.

We have a new group photo. Here is a photo of us!

Show more

Publications

Thumbnail of Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning Paper

Hidde Lycklama, Alexander Viand, Nicolas Küchler, Christian Knabenhans, Anwar Hithnawi

USENIX Security 2024.

Thumbnail of Cohere: Managing Differential Privacy in Large Scale Systems

Cohere: Managing Differential Privacy in Large Scale Systems Paper

Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2024.

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of CoVault: Secure Selective Analytics of Sensitive Data for the Public Good.

CoVault: Secure Selective Analytics of Sensitive Data for the Public Good. Paper

Roberta De Viti, Isaac Sheff, Noemi Glaeser, Baltasar Dinis, Rodrigo Rodrigues, Jonathan Katz, Bobby Bhattacharjee, Anwar Hithnawi, Deepak Garg, Peter Druschel

Preprint, arXiv:2301.08517

Thumbnail of RoFL: Robustness of Secure Federated Learning

RoFL: Robustness of Secure Federated Learning Paper Github

Hidde Lycklama*, Lukas Burkhalter*, Alexander Viand, Nicolas Küchler, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2023.

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?.

VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?. Paper

Jiawei Jiang, Lukas Burkhalter, Fangcheng Fu, Bolin Ding, Bo Du, Anwar Hithnawi, Bo Li, Ce Zhang

NeurIPS (Spotlight) 2022.

Thumbnail of Cryptographic Auditing for Collaborative Learning

Cryptographic Auditing for Collaborative Learning Paper

Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, Anwar Hithnawi

ML Safety Workshop at NeurIPS 2022

Thumbnail of Zeph: Cryptographic Enforcement of End-to-End Data Privacy.

Zeph: Cryptographic Enforcement of End-to-End Data Privacy. Paper Slides Github Video

Lukas Burkhalter*, Nicolas Küchler*, Alexander Viand, Hossein Shafagh, Anwar Hithnawi

USENIX OSDI 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams.

Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams. Paper Slides Github Website Video

Hossein Shafagh, Lukas Burkhalter, Sylvia Ratnasamy, Anwar Hithnawi

USENIX Security 2020.

Thumbnail of TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control.

TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control. Paper Slides Github Website Video

Lukas Burkhalter, Anwar Hithnawi, Alexander Viand, Hossein Shafagh, Sylvia Ratnasamy

USENIX NSDI 2020.

Research Highlights

Verifiable Fully Homomorphic Encryption
Security and Robustness of Collaborative Learning
FHE Development Ecosystem: Tools, Compilers & Challenges
HECO: Fully Homomorphic Encryption Compiler
Zeph: Cryptographic Enforcement of Privacy
Towards Robust FHE for the Real World
Cohere Managing Differential Privacy in Large Scale Systems
RoFL: Robustness of Secure Federated Learning
\ No newline at end of file + gtag('config', 'G-4ZPP8W4RNN');Skip to content

Privacy Preserving Systems Lab

We at the PPS Lab build, investigate, and research software systems for data privacy and data security. Our mission is to develop technologies that enable applications to safely and securely interact with users data while preserving individual's privacy and make it easy for developers to build and develop privacy preserving applications.

Our members are affiliated with the Systems Group and the Applied Cryptography Group at ETH Zurich CS Department.

Projects

Secure and Robust Collaborative Learning thumbnail

Secure and Robust Collaborative Learning

End-to-End Designs for Data Privacy thumbnail

End-to-End Designs for Data Privacy

Accessible Privacy Preserving Computation thumbnail

Accessible Privacy Preserving Computation

Privacy Preserving Stream Analytics at Scale thumbnail

Privacy Preserving Stream Analytics at Scale

News

Arc is accepted at USENIX Security 2024!

Cohere is accepted at IEEE S&P (Oakland) 2024!

We received the best talk award at HotPETs for our work on "Bridging the Gap between Privacy Incidents and PETs"!

Alex successfully defended his PhD thesis last week. Congratulations, Dr. Alex! Photo.

RoFL is accepted at IEEE S&P (Oakland) 2023!

Chris gave talks about Verifiable Fully Homomorphic Encryption at UC Berkeley Sec. Seminar, Stanford Sec. Seminar, Intel Labs, UCSD (invited guest lecture), and the FHE.org conference. Check the talk here.

We received the Google Research Award!

This award will foster a new collaboration with Google that aims to bring efficient and scheme-agnostic FHE support to the TensorFlow framework.

HECO is accepted at USENIX Security 2023!

Congratulations to Lukas Burkhalter, who successfully defended his Ph.D. thesis this week! Photo.

We have a new group photo. Here is a photo of us!

Show more

Publications

Thumbnail of Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning Paper

Hidde Lycklama, Alexander Viand, Nicolas Küchler, Christian Knabenhans, Anwar Hithnawi

USENIX Security 2024.

Thumbnail of Cohere: Managing Differential Privacy in Large Scale Systems

Cohere: Managing Differential Privacy in Large Scale Systems Paper

Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2024.

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github Video

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of CoVault: Secure Selective Analytics of Sensitive Data for the Public Good.

CoVault: Secure Selective Analytics of Sensitive Data for the Public Good. Paper

Roberta De Viti, Isaac Sheff, Noemi Glaeser, Baltasar Dinis, Rodrigo Rodrigues, Jonathan Katz, Bobby Bhattacharjee, Anwar Hithnawi, Deepak Garg, Peter Druschel

Preprint, arXiv:2301.08517

Thumbnail of RoFL: Robustness of Secure Federated Learning

RoFL: Robustness of Secure Federated Learning Paper Github

Hidde Lycklama*, Lukas Burkhalter*, Alexander Viand, Nicolas Küchler, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2023.

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?.

VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?. Paper

Jiawei Jiang, Lukas Burkhalter, Fangcheng Fu, Bolin Ding, Bo Du, Anwar Hithnawi, Bo Li, Ce Zhang

NeurIPS (Spotlight) 2022.

Thumbnail of Cryptographic Auditing for Collaborative Learning

Cryptographic Auditing for Collaborative Learning Paper

Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, Anwar Hithnawi

ML Safety Workshop at NeurIPS 2022

Thumbnail of Zeph: Cryptographic Enforcement of End-to-End Data Privacy.

Zeph: Cryptographic Enforcement of End-to-End Data Privacy. Paper Slides Github Video

Lukas Burkhalter*, Nicolas Küchler*, Alexander Viand, Hossein Shafagh, Anwar Hithnawi

USENIX OSDI 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams.

Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams. Paper Slides Github Website Video

Hossein Shafagh, Lukas Burkhalter, Sylvia Ratnasamy, Anwar Hithnawi

USENIX Security 2020.

Thumbnail of TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control.

TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control. Paper Slides Github Website Video

Lukas Burkhalter, Anwar Hithnawi, Alexander Viand, Hossein Shafagh, Sylvia Ratnasamy

USENIX NSDI 2020.

Research Highlights

Verifiable Fully Homomorphic Encryption
Security and Robustness of Collaborative Learning
FHE Development Ecosystem: Tools, Compilers & Challenges
HECO: Fully Homomorphic Encryption Compiler
Zeph: Cryptographic Enforcement of Privacy
Towards Robust FHE for the Real World
Cohere Managing Differential Privacy in Large Scale Systems
RoFL: Robustness of Secure Federated Learning
\ No newline at end of file diff --git a/people/alexanderviand/index.html b/people/alexanderviand/index.html index 6f63b31a..3678be05 100644 --- a/people/alexanderviand/index.html +++ b/people/alexanderviand/index.html @@ -2,4 +2,4 @@ function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); - gtag('config', 'G-4ZPP8W4RNN');Skip to content
Alexander Viand
Alexander Viand

Making FHE accessible @ Intel Labs

Alexander Viand

I graduated from ETH Zurich in May 2023 and am now continuing similar research at Intel Labs. Before that, I was a doctoral student & research assistant in the Applied Cryptography Group at ETH Zürich and a member of the Privacy Preserving Systems Lab. I also received both my MSc and BSc in Computer Science from ETH Zürich. During my PhD, I had the opportunity to be a visiting scholar with Tobias Grosser at the University of Edinburgh and with Dawn Song at UC Berkeley.

My interests include useable security and privacy, privacy enhancing technologies, and the interactions between these technologies and society. In my research, I work with secure computation technologies including Fully Homomorphic Encryption, Secure Multi-Party Computation and Zero-Knowledge Proofs, trying to make these techniques more accessible to non-experts by developing new systems, tools and abstractions.

I am looking for motivated students who are interested in conducting (potentially industry-based) student thesis or projects related to my research areas. In addition to the projects listed here, you are also very welcome to send me an email to discuss further details or additional project possibilities.

Talks:

FHE Development Ecosystem: Tools, Compilers & Challenges.

HECO: Automatic Code Optimizations for Efficient Fully Homomorphic Encryption.

Building an End-to-End Toolchain for Fully Homomorphic Encryption with MLIR.

Usable FHE: Opportunities & Challenges.

Selected Publications:

Thumbnail of Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning Paper

Hidde Lycklama, Alexander Viand, Nicolas Küchler, Christian Knabenhans, Anwar Hithnawi

USENIX Security 2024.

Thumbnail of Cohere: Managing Differential Privacy in Large Scale Systems

Cohere: Managing Differential Privacy in Large Scale Systems Paper

Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2024.

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of RoFL: Robustness of Secure Federated Learning

RoFL: Robustness of Secure Federated Learning Paper Github

Hidde Lycklama*, Lukas Burkhalter*, Alexander Viand, Nicolas Küchler, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2023.

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of Cryptographic Auditing for Collaborative Learning

Cryptographic Auditing for Collaborative Learning Paper

Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, Anwar Hithnawi

ML Safety Workshop at NeurIPS 2022

Thumbnail of Pyfhel: PYthon For Homomorphic Encryption Libraries

Pyfhel: PYthon For Homomorphic Encryption Libraries Paper Slides Github

Alberto Ibarrondo, Alexander Viand

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '21).

Thumbnail of Private Outsourced Translation for Medical Data.

Private Outsourced Translation for Medical Data. Paper Github

Travis Morrison, Bijeeta Pal, Sarah Scheffler, Alexander Viand

In "Protecting Privacy through Homomorphic Encryption" K. Lauter, W. Dai, and K. Laine, editors. Springer, 2021.

Thumbnail of Zeph: Cryptographic Enforcement of End-to-End Data Privacy.

Zeph: Cryptographic Enforcement of End-to-End Data Privacy. Paper Slides Github Video

Lukas Burkhalter*, Nicolas Küchler*, Alexander Viand, Hossein Shafagh, Anwar Hithnawi

USENIX OSDI 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control.

TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control. Paper Slides Github Website Video

Lukas Burkhalter, Anwar Hithnawi, Alexander Viand, Hossein Shafagh, Sylvia Ratnasamy

USENIX NSDI 2020.

Thumbnail of Robust Secure Aggregation for Privacy-Preserving Federated Learning with Adversaries

Robust Secure Aggregation for Privacy-Preserving Federated Learning with Adversaries Paper

Lukas Burkhalter, Alexander Viand, Matthias Lei, Hossein Shafagh, Anwar Hithnawi

Privacy Preserving Machine Learning Workshop (PPML), 2019.

Thumbnail of Marble: Making Fully Homomorphic Encryption Accessible to All.

Marble: Making Fully Homomorphic Encryption Accessible to All. Paper Github

Alexander Viand, Hossein Shafagh

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '18). Toronto, Canada,

\ No newline at end of file + gtag('config', 'G-4ZPP8W4RNN');Skip to content
Alexander Viand
Alexander Viand

Making FHE accessible @ Intel Labs

Alexander Viand

I graduated from ETH Zurich in May 2023 and am now continuing similar research at Intel Labs. Before that, I was a doctoral student & research assistant in the Applied Cryptography Group at ETH Zürich and a member of the Privacy Preserving Systems Lab. I also received both my MSc and BSc in Computer Science from ETH Zürich. During my PhD, I had the opportunity to be a visiting scholar with Tobias Grosser at the University of Edinburgh and with Dawn Song at UC Berkeley.

My interests include useable security and privacy, privacy enhancing technologies, and the interactions between these technologies and society. In my research, I work with secure computation technologies including Fully Homomorphic Encryption, Secure Multi-Party Computation and Zero-Knowledge Proofs, trying to make these techniques more accessible to non-experts by developing new systems, tools and abstractions.

I am looking for motivated students who are interested in conducting (potentially industry-based) student thesis or projects related to my research areas. In addition to the projects listed here, you are also very welcome to send me an email to discuss further details or additional project possibilities.

Talks:

FHE Development Ecosystem: Tools, Compilers & Challenges.

HECO: Automatic Code Optimizations for Efficient Fully Homomorphic Encryption.

Building an End-to-End Toolchain for Fully Homomorphic Encryption with MLIR.

Usable FHE: Opportunities & Challenges.

Selected Publications:

Thumbnail of Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning Paper

Hidde Lycklama, Alexander Viand, Nicolas Küchler, Christian Knabenhans, Anwar Hithnawi

USENIX Security 2024.

Thumbnail of Cohere: Managing Differential Privacy in Large Scale Systems

Cohere: Managing Differential Privacy in Large Scale Systems Paper

Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2024.

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github Video

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of RoFL: Robustness of Secure Federated Learning

RoFL: Robustness of Secure Federated Learning Paper Github

Hidde Lycklama*, Lukas Burkhalter*, Alexander Viand, Nicolas Küchler, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2023.

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of Cryptographic Auditing for Collaborative Learning

Cryptographic Auditing for Collaborative Learning Paper

Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, Anwar Hithnawi

ML Safety Workshop at NeurIPS 2022

Thumbnail of Pyfhel: PYthon For Homomorphic Encryption Libraries

Pyfhel: PYthon For Homomorphic Encryption Libraries Paper Slides Github

Alberto Ibarrondo, Alexander Viand

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '21).

Thumbnail of Private Outsourced Translation for Medical Data.

Private Outsourced Translation for Medical Data. Paper Github

Travis Morrison, Bijeeta Pal, Sarah Scheffler, Alexander Viand

In "Protecting Privacy through Homomorphic Encryption" K. Lauter, W. Dai, and K. Laine, editors. Springer, 2021.

Thumbnail of Zeph: Cryptographic Enforcement of End-to-End Data Privacy.

Zeph: Cryptographic Enforcement of End-to-End Data Privacy. Paper Slides Github Video

Lukas Burkhalter*, Nicolas Küchler*, Alexander Viand, Hossein Shafagh, Anwar Hithnawi

USENIX OSDI 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control.

TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control. Paper Slides Github Website Video

Lukas Burkhalter, Anwar Hithnawi, Alexander Viand, Hossein Shafagh, Sylvia Ratnasamy

USENIX NSDI 2020.

Thumbnail of Robust Secure Aggregation for Privacy-Preserving Federated Learning with Adversaries

Robust Secure Aggregation for Privacy-Preserving Federated Learning with Adversaries Paper

Lukas Burkhalter, Alexander Viand, Matthias Lei, Hossein Shafagh, Anwar Hithnawi

Privacy Preserving Machine Learning Workshop (PPML), 2019.

Thumbnail of Marble: Making Fully Homomorphic Encryption Accessible to All.

Marble: Making Fully Homomorphic Encryption Accessible to All. Paper Github

Alexander Viand, Hossein Shafagh

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '18). Toronto, Canada,

\ No newline at end of file diff --git a/people/anwarhithnawi/index.html b/people/anwarhithnawi/index.html index 328986c8..88ef5373 100644 --- a/people/anwarhithnawi/index.html +++ b/people/anwarhithnawi/index.html @@ -2,4 +2,4 @@ function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); - gtag('config', 'G-4ZPP8W4RNN');Skip to content
Anwar Hithnawi
Anwar Hithnawi

Group Leader

Anwar Hithnawi

I am an Ambizione Fellow (Principal Investigator) at the Department of Computer Science at ETH Zurich, where I lead the Privacy Preserving Systems Lab. My research focuses on data privacy, applied cryptography, and systems. I completed my Ph.D. in Computer Science at ETH Zurich. Upon graduating, I spent two wonderful years as a postdoc at UC Berkeley. For more information on my current research, please visit the PPS research lab page. Outside of research, I enjoy cycling and swimming.

Research Group [Photos: 2023,2022,2021]

PPS Lab 2023

Current Doctoral Students

  • Nicolas Küchler
  • Hidde Lycklama

Current Master’s and Undergraduate Students

  • Emanuel Opel
  • Isha Gupta
  • Yu-Shan Wei

Former Doctoral Students

  • Alexander Viand ( → Cryptography Researcher at Intel Labs)
    • Thesis: Useable Fully Homomorphic Encryption
    • Committee: Anwar Hithnawi (ETH), Kenny Paterson (ETH), Raluca Ada Popa (UC Berkeley)
  • Lukas Burkhalter [🏅 Microsoft Research Ph.D. Award] ( → Cryptography Engineer at Proton)
    • Thesis: Privacy-Centric Systems for Stream Data Processing
    • Committee: Anwar Hithnawi (ETH), Kenny Paterson (ETH), Peter Druschel (MPI-SWS), Srdjan Capkun (ETH)

Former Master’s and Undergraduate Students

  • Christian Knabenhans (→ Ph.D. student at EPFL)
  • Miro Haller (→ Ph.D. student at UCSD)
  • Marko Mihajlovic (→ Ph.D. student at ETH Zurich)
  • Patrick Jattke (→ Ph.D. student at ETH Zurich)
  • Nicolas Küchler (→ Ph.D. student at ETH Zurich)
  • Hidde Lycklama (→ Ph.D. student at ETH Zurich)
  • Liangcheng Yu (→ Ph.D. student at the University of Pennsylvania)
  • Lukas Burkhalter - [🏅 ETH Medal for Outstanding Master Thesis] (→ Ph.D. student at ETH Zurich)
  • Su Li (→ Ph.D. student at EPFL)
  • Vaibhav Kulkarni (→ Ph.D. student at the University of Lausanne)
  • Yonathan Fisseha (→ Ph.D. student at the University of Michigan)
  • Lena Csomor (→ CS High School Teacher at Kantonsschule Zurcher)
  • Matthias Lei (→ Senior Consultant at Innovation Process Technology)
  • Dominic Plangger (→ Lead Engineer at xorlab)
  • Michel Kaporin (→ Software Engineer at ti&m)
  • Clément Thorens (→ Software Engineer at Huawei Zurich Research Center)

Selected Honors & Awards:

  • Google Research Award.
  • Rising Stars in EECS.
  • Facebook Research Award.
  • Semiconductor Research Corporation Grant.
  • ETH Research Grant.
  • SNF Ambizione Grant.
  • SNF Postdoctoral Fellowship.
  • Google Anita Borg Scholarship.
  • DAAD Scholarship for Master's Studies.

Selected Recent Invited Talks:

  • Upcoming Security and Robustness of Collaborative Learning Systems (invited guest lecture). University of Cambridge. [Slides]
  • Upcoming Holding Secrets Accountable: Auditing Private ML Algorithms. Mapping and Governing the Online World Conference.
  • Useable Fully Homomorphic Encryption: Challenges & Opportunities. Intel Labs. [Slides]
  • Security and Robustness of Collaborative Learning Systems. FLOW Research Seminar, MBZUAI Workshop on CL, University St.Gallen CS Research Seminar, ZISC Seminar, UC Berkeley, MLSys Workshop on Decentralized and Collaborative Learning. [Slides, Video]
  • Systems Designs for End-to-End Privacy. Meta Labs, Columbia University, CISPA, Max Planck. [Slides]
  • Cryptographic Enforcement of End-to-End Data Privacy. Brown University, University of Wisconsin-Madison.
  • Compiler Design for Fully Homomorphic Encryption. Intel's Crypto Frontier Center.
  • Encrypted Data Stream Processing at Scale. Intel, VMware, UC Berkeley.
  • Decentralized Authorization and Access Control for Encrypted Data Streams. UC Berkeley.

Selected Publications:

Thumbnail of Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning Paper

Hidde Lycklama, Alexander Viand, Nicolas Küchler, Christian Knabenhans, Anwar Hithnawi

USENIX Security 2024.

Thumbnail of Cohere: Managing Differential Privacy in Large Scale Systems

Cohere: Managing Differential Privacy in Large Scale Systems Paper

Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2024.

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of CoVault: Secure Selective Analytics of Sensitive Data for the Public Good.

CoVault: Secure Selective Analytics of Sensitive Data for the Public Good. Paper

Roberta De Viti, Isaac Sheff, Noemi Glaeser, Baltasar Dinis, Rodrigo Rodrigues, Jonathan Katz, Bobby Bhattacharjee, Anwar Hithnawi, Deepak Garg, Peter Druschel

Preprint, arXiv:2301.08517

Thumbnail of RoFL: Robustness of Secure Federated Learning

RoFL: Robustness of Secure Federated Learning Paper Github

Hidde Lycklama*, Lukas Burkhalter*, Alexander Viand, Nicolas Küchler, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2023.

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?.

VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?. Paper

Jiawei Jiang, Lukas Burkhalter, Fangcheng Fu, Bolin Ding, Bo Du, Anwar Hithnawi, Bo Li, Ce Zhang

NeurIPS (Spotlight) 2022.

Thumbnail of Cryptographic Auditing for Collaborative Learning

Cryptographic Auditing for Collaborative Learning Paper

Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, Anwar Hithnawi

ML Safety Workshop at NeurIPS 2022

Thumbnail of Zeph: Cryptographic Enforcement of End-to-End Data Privacy.

Zeph: Cryptographic Enforcement of End-to-End Data Privacy. Paper Slides Github Video

Lukas Burkhalter*, Nicolas Küchler*, Alexander Viand, Hossein Shafagh, Anwar Hithnawi

USENIX OSDI 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams.

Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams. Paper Slides Github Website Video

Hossein Shafagh, Lukas Burkhalter, Sylvia Ratnasamy, Anwar Hithnawi

USENIX Security 2020.

Thumbnail of TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control.

TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control. Paper Slides Github Website Video

Lukas Burkhalter, Anwar Hithnawi, Alexander Viand, Hossein Shafagh, Sylvia Ratnasamy

USENIX NSDI 2020.

Thumbnail of Secure Sharing of Partially Homomorphic Encrypted IoT Data.

Secure Sharing of Partially Homomorphic Encrypted IoT Data. Paper

Hossein Shafagh, Anwar Hithnawi, Lukas Burkhalter, Pascal Fischli, Simon Duquennoy

ACM SenSys 2017.

Thumbnail of CrossZig: Combating Cross-Technology Interference in Low-power Wireless Networks.

CrossZig: Combating Cross-Technology Interference in Low-power Wireless Networks. Paper

Anwar Hithnawi, Su Li, Hossein Shafagh, James Gross, Simon Duquennoy

ACM IPSN 2016.

Thumbnail of Talos: Encrypted Query Processing for the Internet of Things.

Talos: Encrypted Query Processing for the Internet of Things. Paper

Hossein Shafagh, Anwar Hithnawi, Andreas Dröscher, Simon Duquennoy, Wen Hu

ACM SenSys 2015.

Thumbnail of TIIM: Technology-Independent Interference Mitigation for Low-power Wireless Networks.

TIIM: Technology-Independent Interference Mitigation for Low-power Wireless Networks. Paper

Anwar Hithnawi, Hossein Shafagh, Simon Duquennoy

ACM IPSN 2015.

Funding:

SNSF
Intel
Meta
Google

\ No newline at end of file + gtag('config', 'G-4ZPP8W4RNN');Skip to content
Anwar Hithnawi
Anwar Hithnawi

Group Leader

Anwar Hithnawi

I am an Ambizione Fellow (Principal Investigator) at the Department of Computer Science at ETH Zurich, where I lead the Privacy Preserving Systems Lab. My research focuses on data privacy, applied cryptography, and systems. I completed my Ph.D. in Computer Science at ETH Zurich. Upon graduating, I spent two wonderful years as a postdoc at UC Berkeley. For more information on my current research, please visit the PPS research lab page. Outside of research, I enjoy cycling and swimming.

Research Group [Photos: 2023,2022,2021]

PPS Lab 2023

Current Doctoral Students

  • Nicolas Küchler
  • Hidde Lycklama

Current Master’s and Undergraduate Students

  • Emanuel Opel
  • Isha Gupta
  • Yu-Shan Wei

Former Doctoral Students

  • Alexander Viand ( → Cryptography Researcher at Intel Labs)
    • Thesis: Useable Fully Homomorphic Encryption
    • Committee: Anwar Hithnawi (ETH), Kenny Paterson (ETH), Raluca Ada Popa (UC Berkeley)
  • Lukas Burkhalter [🏅 Microsoft Research Ph.D. Award] ( → Cryptography Engineer at Proton)
    • Thesis: Privacy-Centric Systems for Stream Data Processing
    • Committee: Anwar Hithnawi (ETH), Kenny Paterson (ETH), Peter Druschel (MPI-SWS), Srdjan Capkun (ETH)

Former Master’s and Undergraduate Students

  • Christian Knabenhans (→ Ph.D. student at EPFL)
  • Miro Haller (→ Ph.D. student at UCSD)
  • Marko Mihajlovic (→ Ph.D. student at ETH Zurich)
  • Patrick Jattke (→ Ph.D. student at ETH Zurich)
  • Nicolas Küchler (→ Ph.D. student at ETH Zurich)
  • Hidde Lycklama (→ Ph.D. student at ETH Zurich)
  • Liangcheng Yu (→ Ph.D. student at the University of Pennsylvania)
  • Lukas Burkhalter - [🏅 ETH Medal for Outstanding Master Thesis] (→ Ph.D. student at ETH Zurich)
  • Su Li (→ Ph.D. student at EPFL)
  • Vaibhav Kulkarni (→ Ph.D. student at the University of Lausanne)
  • Yonathan Fisseha (→ Ph.D. student at the University of Michigan)
  • Lena Csomor (→ CS High School Teacher at Kantonsschule Zurcher)
  • Matthias Lei (→ Senior Consultant at Innovation Process Technology)
  • Dominic Plangger (→ Lead Engineer at xorlab)
  • Michel Kaporin (→ Software Engineer at ti&m)
  • Clément Thorens (→ Software Engineer at Huawei Zurich Research Center)

Selected Honors & Awards:

  • Google Research Award.
  • Rising Stars in EECS.
  • Facebook Research Award.
  • Semiconductor Research Corporation Grant.
  • ETH Research Grant.
  • SNF Ambizione Grant.
  • SNF Postdoctoral Fellowship.
  • Google Anita Borg Scholarship.
  • DAAD Scholarship for Master's Studies.

Selected Recent Invited Talks:

  • Upcoming Security and Robustness of Collaborative Learning Systems (invited guest lecture). University of Cambridge. [Slides]
  • Upcoming Holding Secrets Accountable: Auditing Private ML Algorithms. Mapping and Governing the Online World Conference.
  • Useable Fully Homomorphic Encryption: Challenges & Opportunities. Intel Labs. [Slides]
  • Security and Robustness of Collaborative Learning Systems. FLOW Research Seminar, MBZUAI Workshop on CL, University St.Gallen CS Research Seminar, ZISC Seminar, UC Berkeley, MLSys Workshop on Decentralized and Collaborative Learning. [Slides, Video]
  • Systems Designs for End-to-End Privacy. Meta Labs, Columbia University, CISPA, Max Planck. [Slides]
  • Cryptographic Enforcement of End-to-End Data Privacy. Brown University, University of Wisconsin-Madison.
  • Compiler Design for Fully Homomorphic Encryption. Intel's Crypto Frontier Center.
  • Encrypted Data Stream Processing at Scale. Intel, VMware, UC Berkeley.
  • Decentralized Authorization and Access Control for Encrypted Data Streams. UC Berkeley.

Selected Publications:

Thumbnail of Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning Paper

Hidde Lycklama, Alexander Viand, Nicolas Küchler, Christian Knabenhans, Anwar Hithnawi

USENIX Security 2024.

Thumbnail of Cohere: Managing Differential Privacy in Large Scale Systems

Cohere: Managing Differential Privacy in Large Scale Systems Paper

Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2024.

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github Video

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of CoVault: Secure Selective Analytics of Sensitive Data for the Public Good.

CoVault: Secure Selective Analytics of Sensitive Data for the Public Good. Paper

Roberta De Viti, Isaac Sheff, Noemi Glaeser, Baltasar Dinis, Rodrigo Rodrigues, Jonathan Katz, Bobby Bhattacharjee, Anwar Hithnawi, Deepak Garg, Peter Druschel

Preprint, arXiv:2301.08517

Thumbnail of RoFL: Robustness of Secure Federated Learning

RoFL: Robustness of Secure Federated Learning Paper Github

Hidde Lycklama*, Lukas Burkhalter*, Alexander Viand, Nicolas Küchler, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2023.

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?.

VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?. Paper

Jiawei Jiang, Lukas Burkhalter, Fangcheng Fu, Bolin Ding, Bo Du, Anwar Hithnawi, Bo Li, Ce Zhang

NeurIPS (Spotlight) 2022.

Thumbnail of Cryptographic Auditing for Collaborative Learning

Cryptographic Auditing for Collaborative Learning Paper

Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, Anwar Hithnawi

ML Safety Workshop at NeurIPS 2022

Thumbnail of Zeph: Cryptographic Enforcement of End-to-End Data Privacy.

Zeph: Cryptographic Enforcement of End-to-End Data Privacy. Paper Slides Github Video

Lukas Burkhalter*, Nicolas Küchler*, Alexander Viand, Hossein Shafagh, Anwar Hithnawi

USENIX OSDI 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams.

Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams. Paper Slides Github Website Video

Hossein Shafagh, Lukas Burkhalter, Sylvia Ratnasamy, Anwar Hithnawi

USENIX Security 2020.

Thumbnail of TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control.

TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control. Paper Slides Github Website Video

Lukas Burkhalter, Anwar Hithnawi, Alexander Viand, Hossein Shafagh, Sylvia Ratnasamy

USENIX NSDI 2020.

Thumbnail of Secure Sharing of Partially Homomorphic Encrypted IoT Data.

Secure Sharing of Partially Homomorphic Encrypted IoT Data. Paper

Hossein Shafagh, Anwar Hithnawi, Lukas Burkhalter, Pascal Fischli, Simon Duquennoy

ACM SenSys 2017.

Thumbnail of CrossZig: Combating Cross-Technology Interference in Low-power Wireless Networks.

CrossZig: Combating Cross-Technology Interference in Low-power Wireless Networks. Paper

Anwar Hithnawi, Su Li, Hossein Shafagh, James Gross, Simon Duquennoy

ACM IPSN 2016.

Thumbnail of Talos: Encrypted Query Processing for the Internet of Things.

Talos: Encrypted Query Processing for the Internet of Things. Paper

Hossein Shafagh, Anwar Hithnawi, Andreas Dröscher, Simon Duquennoy, Wen Hu

ACM SenSys 2015.

Thumbnail of TIIM: Technology-Independent Interference Mitigation for Low-power Wireless Networks.

TIIM: Technology-Independent Interference Mitigation for Low-power Wireless Networks. Paper

Anwar Hithnawi, Hossein Shafagh, Simon Duquennoy

ACM IPSN 2015.

Funding:

SNSF
Intel
Meta
Google

\ No newline at end of file diff --git a/publications/fhe/index.html b/publications/fhe/index.html index a361c3df..08384b4a 100644 --- a/publications/fhe/index.html +++ b/publications/fhe/index.html @@ -2,4 +2,4 @@ function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); - gtag('config', 'G-4ZPP8W4RNN');Skip to content

SoK: Fully Homomorphic Encryption Compilers.

's image

``

People

Publications

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of Pyfhel: PYthon For Homomorphic Encryption Libraries

Pyfhel: PYthon For Homomorphic Encryption Libraries Paper Slides Github

Alberto Ibarrondo, Alexander Viand

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '21).

Thumbnail of Private Outsourced Translation for Medical Data.

Private Outsourced Translation for Medical Data. Paper Github

Travis Morrison, Bijeeta Pal, Sarah Scheffler, Alexander Viand

In "Protecting Privacy through Homomorphic Encryption" K. Lauter, W. Dai, and K. Laine, editors. Springer, 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of Marble: Making Fully Homomorphic Encryption Accessible to All.

Marble: Making Fully Homomorphic Encryption Accessible to All. Paper Github

Alexander Viand, Hossein Shafagh

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '18). Toronto, Canada,

\ No newline at end of file + gtag('config', 'G-4ZPP8W4RNN');Skip to content

SoK: Fully Homomorphic Encryption Compilers.

's image

``

People

Publications

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github Video

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of Pyfhel: PYthon For Homomorphic Encryption Libraries

Pyfhel: PYthon For Homomorphic Encryption Libraries Paper Slides Github

Alberto Ibarrondo, Alexander Viand

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '21).

Thumbnail of Private Outsourced Translation for Medical Data.

Private Outsourced Translation for Medical Data. Paper Github

Travis Morrison, Bijeeta Pal, Sarah Scheffler, Alexander Viand

In "Protecting Privacy through Homomorphic Encryption" K. Lauter, W. Dai, and K. Laine, editors. Springer, 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of Marble: Making Fully Homomorphic Encryption Accessible to All.

Marble: Making Fully Homomorphic Encryption Accessible to All. Paper Github

Alexander Viand, Hossein Shafagh

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '18). Toronto, Canada,

\ No newline at end of file diff --git a/publications/index.html b/publications/index.html index 227b7c9f..f91e3242 100644 --- a/publications/index.html +++ b/publications/index.html @@ -2,4 +2,4 @@ function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); - gtag('config', 'G-4ZPP8W4RNN');Skip to content

Publications

Thumbnail of Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning Paper

Hidde Lycklama, Alexander Viand, Nicolas Küchler, Christian Knabenhans, Anwar Hithnawi

USENIX Security 2024.

Thumbnail of Cohere: Managing Differential Privacy in Large Scale Systems

Cohere: Managing Differential Privacy in Large Scale Systems Paper

Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2024.

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of CoVault: Secure Selective Analytics of Sensitive Data for the Public Good.

CoVault: Secure Selective Analytics of Sensitive Data for the Public Good. Paper

Roberta De Viti, Isaac Sheff, Noemi Glaeser, Baltasar Dinis, Rodrigo Rodrigues, Jonathan Katz, Bobby Bhattacharjee, Anwar Hithnawi, Deepak Garg, Peter Druschel

Preprint, arXiv:2301.08517

Thumbnail of RoFL: Robustness of Secure Federated Learning

RoFL: Robustness of Secure Federated Learning Paper Github

Hidde Lycklama*, Lukas Burkhalter*, Alexander Viand, Nicolas Küchler, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2023.

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?.

VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?. Paper

Jiawei Jiang, Lukas Burkhalter, Fangcheng Fu, Bolin Ding, Bo Du, Anwar Hithnawi, Bo Li, Ce Zhang

NeurIPS (Spotlight) 2022.

Thumbnail of Cryptographic Auditing for Collaborative Learning

Cryptographic Auditing for Collaborative Learning Paper

Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, Anwar Hithnawi

ML Safety Workshop at NeurIPS 2022

Thumbnail of Zeph: Cryptographic Enforcement of End-to-End Data Privacy.

Zeph: Cryptographic Enforcement of End-to-End Data Privacy. Paper Slides Github Video

Lukas Burkhalter*, Nicolas Küchler*, Alexander Viand, Hossein Shafagh, Anwar Hithnawi

USENIX OSDI 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams.

Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams. Paper Slides Github Website Video

Hossein Shafagh, Lukas Burkhalter, Sylvia Ratnasamy, Anwar Hithnawi

USENIX Security 2020.

Thumbnail of TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control.

TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control. Paper Slides Github Website Video

Lukas Burkhalter, Anwar Hithnawi, Alexander Viand, Hossein Shafagh, Sylvia Ratnasamy

USENIX NSDI 2020.

\ No newline at end of file + gtag('config', 'G-4ZPP8W4RNN');Skip to content

Publications

Thumbnail of Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning Paper

Hidde Lycklama, Alexander Viand, Nicolas Küchler, Christian Knabenhans, Anwar Hithnawi

USENIX Security 2024.

Thumbnail of Cohere: Managing Differential Privacy in Large Scale Systems

Cohere: Managing Differential Privacy in Large Scale Systems Paper

Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2024.

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github Video

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of CoVault: Secure Selective Analytics of Sensitive Data for the Public Good.

CoVault: Secure Selective Analytics of Sensitive Data for the Public Good. Paper

Roberta De Viti, Isaac Sheff, Noemi Glaeser, Baltasar Dinis, Rodrigo Rodrigues, Jonathan Katz, Bobby Bhattacharjee, Anwar Hithnawi, Deepak Garg, Peter Druschel

Preprint, arXiv:2301.08517

Thumbnail of RoFL: Robustness of Secure Federated Learning

RoFL: Robustness of Secure Federated Learning Paper Github

Hidde Lycklama*, Lukas Burkhalter*, Alexander Viand, Nicolas Küchler, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2023.

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?.

VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?. Paper

Jiawei Jiang, Lukas Burkhalter, Fangcheng Fu, Bolin Ding, Bo Du, Anwar Hithnawi, Bo Li, Ce Zhang

NeurIPS (Spotlight) 2022.

Thumbnail of Cryptographic Auditing for Collaborative Learning

Cryptographic Auditing for Collaborative Learning Paper

Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, Anwar Hithnawi

ML Safety Workshop at NeurIPS 2022

Thumbnail of Zeph: Cryptographic Enforcement of End-to-End Data Privacy.

Zeph: Cryptographic Enforcement of End-to-End Data Privacy. Paper Slides Github Video

Lukas Burkhalter*, Nicolas Küchler*, Alexander Viand, Hossein Shafagh, Anwar Hithnawi

USENIX OSDI 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams.

Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams. Paper Slides Github Website Video

Hossein Shafagh, Lukas Burkhalter, Sylvia Ratnasamy, Anwar Hithnawi

USENIX Security 2020.

Thumbnail of TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control.

TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control. Paper Slides Github Website Video

Lukas Burkhalter, Anwar Hithnawi, Alexander Viand, Hossein Shafagh, Sylvia Ratnasamy

USENIX NSDI 2020.

\ No newline at end of file diff --git a/research/fhe/index.html b/research/fhe/index.html index 1cbf403e..db6e3fb1 100644 --- a/research/fhe/index.html +++ b/research/fhe/index.html @@ -2,4 +2,4 @@ function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); - gtag('config', 'G-4ZPP8W4RNN');Skip to content

Accessible Privacy Preserving Computation

's image

Privacy and security are gaining tremendous importance across all organizations as public perception of these issues has shifted and expectations, including regulatory demands, have increased. This, in turn, has led organizations to adopt stronger security and privacy protection. Although industry best practice such as in-transit and at-rest encryption provide important protection for user data, the need to decrypt data to compute on it (in-use) still exposes the data to a wide variety of threats. Secure computation techniques such as fully homomorphic encryption (FHE), which allows a third party to perform arbitrary computations on encrypted data, address this gap. In recent years, we have seen a leap in performance in FHE driven by a series of breakthroughs and advancements that have propelled FHE into the realm of practical applications. With hardware accelerators on the horizon, FHE will soon be competitive for a wide range of applications. However, applying FHE in practice is notoriously difficult. Deploying FHE in practice and at scale is today hindered primarily by its complexity rather than its performance potential. The performance characteristics of FHE are nonintuitive and highly contextual, and anticipating them requires significant experience and expertise. The next leap towards broader adoption of FHE requires designing and building a development ecosystem for FHE that facilitates FHE application development. We need to provide the right abstractions and automatic optimizations to tame the current complexity of FHE development and deliver on the performance potential of FHE. The aim of this work is to build the tools for an accessible FHE development ecosystem.


• The State of Fully Homomorphic Encryption Compilers (Published in IEEE S&P’21): Fully Homomorphic Encryption allows a third party to perform arbitrary computations on encrypted data, learning neither the inputs nor the computation results. Hence, it provides resilience in situations where computations are carried out by an untrusted or potentially compromised party. This powerful concept was first conceived by Rivest et al. in the 1970s. However, it remained unrealized until Craig Gentry presented the first feasible FHE scheme in 2009. Since then, FHE has gone from theoretical breakthrough to practical deployment. However, developing FHE systems remains complex, requiring expert knowledge. In this work, we outline the inherent engineering challenges in developing FHE applications and discuss how tools like compilers that translate between standard programs and FHE implementations can step in to address some of these complexities. We survey, evaluate, and systematize FHE tools and compilers. Using different case study applications that represent common aspects of FHE applications, highlight where barriers to entry have been successfully lowered and where they still remain.


• HECO (Published in USENIX Security’23): FHE imposes a fundamentally different programming paradigm. This arises not only because the security guarantees imply programs must be data independent but also because FHE ciphertexts deteriorate during homomorphic operations, which must be carefully managed. In addition, many schemes feature powerful inherent parallelism. However, fully exploiting this feature requires significant rethinking and redesigning of applications and algorithms to match the FHE programming paradigm. As a result of these challenges, a vast gap currently exists between state-of-the-art performance results and what non-experts can achieve themselves. Towards this, we developed HECO, an end-to-end compiler for FHE that aims aims to enable non-experts to develop secure and efficient FHE applications. At its core is a program transformation logic that translates standard high-level imperative code to the unique programming paradigm of FHE. From an unoptimized high-level input, our compiler can generate code that matches the performance of code written by an expert.



• Verifiable Fully Homomorphic Encryption: FHE is seeing increasing real-world deployment to protect data in use by allowing computation over encrypted data. However, the same malleability that enables homomorphic computations also raises integrity issues, which have so far been mostly overlooked. While FHE’s lack of integrity has obvious implications for correctness, it also has severe implications for confidentiality: a malicious server can leverage the lack of integrity to carry out interactive key-recovery attacks. As a result, virtually all FHE schemes and applications assume an honest-but-curious server who does not deviate from the protocol. This assumption is insufficient for a wide range of critical deployment scenarios. While there has been work that aims to address this gap, these have remained isolated efforts considering only aspects of the overall problem and fail to fully address the needs and characteristics of modern FHE schemes and applications. In this project, we analyze existing FHE integrity approaches, present attacks that exploit gaps in prior work, and propose a new notion for maliciously-secure verifiable FHE. We then instantiate this new notion with a range of techniques, analyzing them and evaluating their performance in a range of different settings.


• Intermediate Representations (IRs) Standards for FHE : Current FHE toolchains are standalone and generally not cross-compatible, and compilers frequently use ad hoc IRs and output formats. Not only does this lead to a substantial waste of development resources spent re-implementing common functionality, it also means developers cannot easily switch their approach or mix and match tools to exploit their strengths fully. We are working on designing common abstractions for FHE compilers and tools, including sets of IRs (e.g., MLIR dialects) that capture the information required for complex optimizations while still allowing easy lowering to simpler representations. To ensure this standardization reflects the community needs, we initiated an effort that brings together major players (i.e., ZAMA, Intel, Microsoft, Google) working on tools for FHE development. If you are interested in joining these meetings, please contact us.


People

Alexander Viand
Alexander Viand

Making FHE accessible @ Intel Labs

Anwar Hithnawi
Anwar Hithnawi

Group Leader

Publications

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of Pyfhel: PYthon For Homomorphic Encryption Libraries

Pyfhel: PYthon For Homomorphic Encryption Libraries Paper Slides Github

Alberto Ibarrondo, Alexander Viand

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '21).

Thumbnail of Private Outsourced Translation for Medical Data.

Private Outsourced Translation for Medical Data. Paper Github

Travis Morrison, Bijeeta Pal, Sarah Scheffler, Alexander Viand

In "Protecting Privacy through Homomorphic Encryption" K. Lauter, W. Dai, and K. Laine, editors. Springer, 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of Marble: Making Fully Homomorphic Encryption Accessible to All.

Marble: Making Fully Homomorphic Encryption Accessible to All. Paper Github

Alexander Viand, Hossein Shafagh

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '18). Toronto, Canada,

\ No newline at end of file + gtag('config', 'G-4ZPP8W4RNN');Skip to content

Accessible Privacy Preserving Computation

's image

Privacy and security are gaining tremendous importance across all organizations as public perception of these issues has shifted and expectations, including regulatory demands, have increased. This, in turn, has led organizations to adopt stronger security and privacy protection. Although industry best practice such as in-transit and at-rest encryption provide important protection for user data, the need to decrypt data to compute on it (in-use) still exposes the data to a wide variety of threats. Secure computation techniques such as fully homomorphic encryption (FHE), which allows a third party to perform arbitrary computations on encrypted data, address this gap. In recent years, we have seen a leap in performance in FHE driven by a series of breakthroughs and advancements that have propelled FHE into the realm of practical applications. With hardware accelerators on the horizon, FHE will soon be competitive for a wide range of applications. However, applying FHE in practice is notoriously difficult. Deploying FHE in practice and at scale is today hindered primarily by its complexity rather than its performance potential. The performance characteristics of FHE are nonintuitive and highly contextual, and anticipating them requires significant experience and expertise. The next leap towards broader adoption of FHE requires designing and building a development ecosystem for FHE that facilitates FHE application development. We need to provide the right abstractions and automatic optimizations to tame the current complexity of FHE development and deliver on the performance potential of FHE. The aim of this work is to build the tools for an accessible FHE development ecosystem.


• The State of Fully Homomorphic Encryption Compilers (Published in IEEE S&P’21): Fully Homomorphic Encryption allows a third party to perform arbitrary computations on encrypted data, learning neither the inputs nor the computation results. Hence, it provides resilience in situations where computations are carried out by an untrusted or potentially compromised party. This powerful concept was first conceived by Rivest et al. in the 1970s. However, it remained unrealized until Craig Gentry presented the first feasible FHE scheme in 2009. Since then, FHE has gone from theoretical breakthrough to practical deployment. However, developing FHE systems remains complex, requiring expert knowledge. In this work, we outline the inherent engineering challenges in developing FHE applications and discuss how tools like compilers that translate between standard programs and FHE implementations can step in to address some of these complexities. We survey, evaluate, and systematize FHE tools and compilers. Using different case study applications that represent common aspects of FHE applications, highlight where barriers to entry have been successfully lowered and where they still remain.


• HECO (Published in USENIX Security’23): FHE imposes a fundamentally different programming paradigm. This arises not only because the security guarantees imply programs must be data independent but also because FHE ciphertexts deteriorate during homomorphic operations, which must be carefully managed. In addition, many schemes feature powerful inherent parallelism. However, fully exploiting this feature requires significant rethinking and redesigning of applications and algorithms to match the FHE programming paradigm. As a result of these challenges, a vast gap currently exists between state-of-the-art performance results and what non-experts can achieve themselves. Towards this, we developed HECO, an end-to-end compiler for FHE that aims aims to enable non-experts to develop secure and efficient FHE applications. At its core is a program transformation logic that translates standard high-level imperative code to the unique programming paradigm of FHE. From an unoptimized high-level input, our compiler can generate code that matches the performance of code written by an expert.



• Verifiable Fully Homomorphic Encryption: FHE is seeing increasing real-world deployment to protect data in use by allowing computation over encrypted data. However, the same malleability that enables homomorphic computations also raises integrity issues, which have so far been mostly overlooked. While FHE’s lack of integrity has obvious implications for correctness, it also has severe implications for confidentiality: a malicious server can leverage the lack of integrity to carry out interactive key-recovery attacks. As a result, virtually all FHE schemes and applications assume an honest-but-curious server who does not deviate from the protocol. This assumption is insufficient for a wide range of critical deployment scenarios. While there has been work that aims to address this gap, these have remained isolated efforts considering only aspects of the overall problem and fail to fully address the needs and characteristics of modern FHE schemes and applications. In this project, we analyze existing FHE integrity approaches, present attacks that exploit gaps in prior work, and propose a new notion for maliciously-secure verifiable FHE. We then instantiate this new notion with a range of techniques, analyzing them and evaluating their performance in a range of different settings.


• Intermediate Representations (IRs) Standards for FHE : Current FHE toolchains are standalone and generally not cross-compatible, and compilers frequently use ad hoc IRs and output formats. Not only does this lead to a substantial waste of development resources spent re-implementing common functionality, it also means developers cannot easily switch their approach or mix and match tools to exploit their strengths fully. We are working on designing common abstractions for FHE compilers and tools, including sets of IRs (e.g., MLIR dialects) that capture the information required for complex optimizations while still allowing easy lowering to simpler representations. To ensure this standardization reflects the community needs, we initiated an effort that brings together major players (i.e., ZAMA, Intel, Microsoft, Google) working on tools for FHE development. If you are interested in joining these meetings, please contact us.


People

Alexander Viand
Alexander Viand

Making FHE accessible @ Intel Labs

Anwar Hithnawi
Anwar Hithnawi

Group Leader

Publications

Thumbnail of Verifiable Fully Homomorphic Encryption

Verifiable Fully Homomorphic Encryption Paper Github Video

Alexander Viand*, Christian Knabenhans, Anwar Hithnawi

Preprint, arXiv:2301.07041

Thumbnail of HECO: Fully Homomorphic Encryption Compiler.

HECO: Fully Homomorphic Encryption Compiler. Paper Github

Alexander Viand, Patrick Jattke, Miro Haller, Anwar Hithnawi

USENIX Security 2023.

Thumbnail of Pyfhel: PYthon For Homomorphic Encryption Libraries

Pyfhel: PYthon For Homomorphic Encryption Libraries Paper Slides Github

Alberto Ibarrondo, Alexander Viand

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '21).

Thumbnail of Private Outsourced Translation for Medical Data.

Private Outsourced Translation for Medical Data. Paper Github

Travis Morrison, Bijeeta Pal, Sarah Scheffler, Alexander Viand

In "Protecting Privacy through Homomorphic Encryption" K. Lauter, W. Dai, and K. Laine, editors. Springer, 2021.

Thumbnail of SoK: Fully Homomorphic Encryption Compilers.

SoK: Fully Homomorphic Encryption Compilers. Paper Slides Github Website Video

Alexander Viand, Patrick Jattke, Anwar Hithnawi

IEEE Security and Privacy (Oakland) 2021.

Thumbnail of Marble: Making Fully Homomorphic Encryption Accessible to All.

Marble: Making Fully Homomorphic Encryption Accessible to All. Paper Github

Alexander Viand, Hossein Shafagh

Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '18). Toronto, Canada,

\ No newline at end of file