cleverhans
Adversarial example library
A Python library for benchmarking machine learning systems' vulnerability to adversarial examples.
An adversarial example library for constructing attacks, building defenses, and benchmarking both
6k stars
190 watching
1k forks
Language: Jupyter Notebook
last commit: 11 months ago benchmarkingmachine-learningsecurity
Related projects:
| Repository | Description | Stars |
|---|---|---|
 trusted-ai/adversarial-robustness-toolbox | A Python library that provides tools and techniques to defend against various attacks on machine learning models and applications. | 4,945 |
 utkuozbulak/pytorch-cnn-adversarial-attacks | PyTorch implementation of various Convolutional Neural Network adversarial attack techniques | 354 |
 ahkarami/deep-learning-in-production | A collection of notes and references on deploying deep learning models in production environments | 4,313 |
 trekhleb/homemade-machine-learning | Practices implementing popular machine learning algorithms from scratch to gain a deeper understanding of their mathematics | 23,191 |
 thu-ml/tianshou | A high-performance reinforcement learning library with modular interfaces and user-friendly APIs for building deep learning agents. | 8,069 |
 ys-zong/foolyourvllms | An attack framework to manipulate the output of large language models and vision-language models | 14 |
 tensorflow/agents | A library for implementing and deploying reinforcement learning algorithms using TensorFlow. | 2,816 |
 yunjey/pytorch-tutorial | A comprehensive tutorial project that provides code examples for learning PyTorch by implementing various deep learning models and demonstrating their usage. | 30,401 |
 pytorch/examples | A collection of curated examples showcasing various PyTorch applications in computer vision, natural language processing, and reinforcement learning. | 22,530 |
 jind11/textfooler | A tool for generating adversarial examples to attack text classification and inference models | 496 |
 thunlp/openattack | A Python toolkit for generating adversarial examples to test the robustness of natural language processing models | 699 |
 eth-sri/diffai | Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques. | 219 |
 advboxes/advbox | A toolbox for generating adversarial examples to test the robustness of machine learning models | 1,389 |
 eriklindernoren/pytorch-gan | A collection of PyTorch implementations of Generative Adversarial Networks for image synthesis and other applications. | 16,570 |
 qdata/textattack | A framework for creating and testing robust NLP models by generating adversarial examples and augmenting datasets. | 3,015 |