softsys4ai / athena
Athena: A Framework for Defending Machine Learning Systems Against Adversarial Attacks
☆41Updated 2 years ago
Related projects: ⓘ
- Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs (ACM CCS'21)☆17Updated last year
- Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks [NeurIPS 2019]☆49Updated 4 years ago
- Code release for the ICML 2019 paper "Are generative classifiers more robust to adversarial attacks?"☆23Updated 5 years ago
- A general method for training cost-sensitive robust classifier☆21Updated 5 years ago
- EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples☆37Updated 5 years ago
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆24Updated 2 years ago
- CROWN: A Neural Network Verification Framework for Networks with General Activation Functions☆38Updated 5 years ago
- ☆11Updated 4 years ago
- Codebase for the paper "Adversarial Attacks on Time Series"☆18Updated 5 years ago
- A community-run reference for state-of-the-art adversarial example defenses.☆49Updated last year
- Certifying Geometric Robustness of Neural Networks☆15Updated last year
- Codes for reproducing the white-box adversarial attacks in “EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples,” …☆21Updated 5 years ago
- Interval attacks (adversarial ML)☆21Updated 5 years ago
- Codes for reproducing the robustness evaluation scores in “Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approac…☆47Updated 6 years ago
- ☆18Updated 4 years ago
- ☆82Updated 10 months ago
- A curated list of awesome resources regarding machine learning reliability.☆30Updated 3 years ago
- Towards Reverse-Engineering Black-Box Neural Networks, ICLR'18☆53Updated 5 years ago
- Tensorflow implementation of Meta Adversarial Training for Adversarial Patch Attacks on Tiny ImageNet.☆25Updated 3 years ago
- Codes for reproducing the black-box adversarial attacks in “ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Network…☆54Updated 5 years ago
- Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019☆47Updated last year
- Learning perturbation sets for robust machine learning☆64Updated 3 years ago
- An (imperfect) implementation of wide resnets and Parseval regularization☆8Updated 4 years ago
- Unofficial implementation of the paper 'Adversarial Training for Free'☆20Updated 5 years ago
- ☆22Updated last year
- Circumventing the defense in "Ensemble Adversarial Training: Attacks and Defenses"☆39Updated 6 years ago
- [ICML 2019, 20 min long talk] Robust Decision Trees Against Adversarial Examples☆66Updated last year
- [ICLR 2021: Spotlight] Source code for the paper "A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Infer…☆15Updated 2 years ago
- ☆21Updated 3 years ago
- Implement adversarial arrack on Recurrent Neural network built to perform sentiment analysis with LSTM using TensorFlow☆21Updated 5 years ago