Privacy Testing for Deep Learning

A micro-service reference test application for model extraction, cloud management, energy efficiency, power prediction, single- and multi-tier auto-scaling

General-purpose library for extracting interpretable models from Multi-Agent Reinforcement Learning systems

Analytic tableau based minimal model generator, model checker and theorem prover for first-order logic with modal extensions

MEME: Generating RNN Model Explanations via Model Extraction

Simple machine learning in Python/Tensorflow with model saving

Ecore metamodel reverse engineering: Automatically extract EMF metamodels from Java code.

CME: Concept-based Model Extraction

📄 [Talk] OFFZONE 2022 / ODS Data Halloween 2022: Black-box attacks on ML models + with use of open-source tools

For our AAAI23 paper "DisGUIDE: Disagreement-Guided Data-Free Model Extraction" (Oral Presentation) by Jonathan Rosenthal, Eric Enouen, Hung Viet Pham, and Lin Tan.

Marich is a model-agnostic extraction algorithm. It uses a public data to query a private model, aggregates the predicted labels, and construct a distributionall equivalent/max-information leaking extracted model.

A neural network model builder, leveraging a neuro-symbolic interface.

The Labelled Transition Systems Extractor tool project

Model Reconstruction from Counterfactual Explanations

Collection of the TeX files and figures used to create my UofA CS master's thesis

Extension for the LTS Extractor platform, which is used for enabling the communication with the methods for generating model analysis, and to ease the management of log files throughout the platform.

Serverless Application Extraction System (SAES)