adversarial-robustness-toolbox
ML defense toolkit
A Python library that provides tools and techniques to defend against various attacks on machine learning models and applications.
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
5k stars
98 watching
1k forks
Language: Python
last commit: 6 days ago
Linked from 1 awesome list
adversarial-attacksadversarial-examplesadversarial-machine-learningaiartificial-intelligenceattackblue-teamevasionextractioninferencemachine-learningpoisoningprivacypythonred-teamtrusted-aitrustworthy-ai
ethicalml/awesome-production-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
 borealisai/advertorch | A toolbox for researching and evaluating robustness against attacks on machine learning models | 1,308 |
 cleverhans-lab/cleverhans | A Python library for benchmarking machine learning systems' vulnerability to adversarial examples. | 6,202 |
| trusted-ai/aix360 | A toolkit for explaining complex AI models and data-driven insights | 1,633 |
 guanghelee/neurips19-certificates-of-robustness | Tight certificates of adversarial robustness for randomly smoothed classifiers | 17 |
| trusted-ai/aif360 | A comprehensive toolkit for detecting and mitigating bias in machine learning models and datasets. | 2,457 |
 eth-sri/diffai | Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques. | 218 |
 yunqing-me/attackvlm | An adversarial attack framework on large vision-language models | 161 |
 mitre/advmlthreatmatrix | A framework to help security analysts understand and prepare for adversarial machine learning attacks on AI systems | 1,050 |
 jhayes14/adversarial-patch | A PyTorch implementation of an adversarial patch system to defend against image attacks | 204 |
 thunlp/openattack | A Python toolkit for generating adversarial examples to test the robustness of natural language processing models | 689 |
 azure/pyrit | Automates security risk identification and red teaming in generative AI systems | 1,891 |
 edisonleeeee/greatx | A toolbox for graph reliability and robustness against noise, distribution shifts, and attacks. | 83 |
 airbnb/artificial-adversary | A tool to generate adversarial text examples and test machine learning models against them | 397 |
 utkuozbulak/pytorch-cnn-adversarial-attacks | PyTorch implementation of various Convolutional Neural Network adversarial attack techniques | 350 |
 clementsicard/reliable-and-trustworthy-ai-notebooks | Research-focused notebooks on developing robust and secure AI models against adversarial attacks | 1 |