Open-Source-Backdoor-Learning

official/unofficial open source code/dataset for backdoor attack and defense

Model based Defense

Tensorflow

TABOR https://github.com/UsmannK/TABOR

Neural Cleanse https://github.com/trx14/TrojanNet/tree/master/code/Detection/neural_cleanese

ABS https://github.com/naiyeleo/ABS

NEO https://github.com/sakshiudeshi/Neo

On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping https://github.com/Sanghyun-Hong/Gradient-Shaping

Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection https://github.com/TDteach/Demon-in-the-Variant

DL-TND https://github.com/wangren09/TrojanNetDetector

NNoculation https://github.com/akshajkumarv/NNoculation

Deepsweep https://github.com/YiZeng623/DeepSweep

Pytorch

Neural Cleanse https://github.com/VinAIResearch/input-aware-backdoor-attack-release

Fine-pruning https://github.com/VinAIResearch/input-aware-backdoor-attack-release

Februus https://github.com/AdelaideAuto-IDLab/Februus

Adversarial Unlearning of Backdoors via Implicit Hypergradient https://github.com/YiZeng623/I-BAU_Adversarial_Unlearning_of-Backdoors_via_implicit_Hypergradient

Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness https://github.com/IBM/model-sanitization

Backdoor Scanning for Deep Neural Networks through K-Arm Optimization https://github.com/PurduePAML/K-ARM_Backdoor_Optimization

Defending-Neural-Backdoors-via-Generative-Distribution-Modeling https://github.com/superrrpotato/Defending-Neural-Backdoors-via-Generative-Distribution-Modeling

ULP https://github.com/UMBCvision/Universal-Litmus-Patterns

Input based Defense

Pytorch

STRIP https://github.com/VinAIResearch/input-aware-backdoor-attack-release

Tensorflow

STRIP https://github.com/garrisongys/STRIP

Spectral https://github.com/AdvDoor/AdvDoor

Comprehensive https://github.com/MadryLab/backdoor_data_poisoning

Activation Clustering https://github.com/AdvDoor/AdvDoor

Activation Clustering https://github.com/Trusted-AI/adversarial-robustness-toolbox/blob/main/art/defences/detector/poison/activation_defence.py

Julia

Spectre https://github.com/SewoongLab/spectre-defense

Comprehensive Toolkit

ART https://github.com/Trusted-AI/adversarial-robustness-toolbox