softsys4ai / athena
Athena: A Framework for Defending Machine Learning Systems Against Adversarial Attacks
☆42Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for athena
- Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs (ACM CCS'21)☆17Updated last year
- Code release for the ICML 2019 paper "Are generative classifiers more robust to adversarial attacks?"☆23Updated 5 years ago
- EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples☆38Updated 6 years ago
- Codes for reproducing the white-box adversarial attacks in “EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples,” …☆21Updated 6 years ago
- Towards Reverse-Engineering Black-Box Neural Networks, ICLR'18☆54Updated 5 years ago
- Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks [NeurIPS 2019]☆50Updated 4 years ago
- A community-run reference for state-of-the-art adversarial example defenses.☆49Updated last month
- CROWN: A Neural Network Verification Framework for Networks with General Activation Functions☆38Updated 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
- ☆11Updated 4 years ago
- Codes for reproducing the black-box adversarial attacks in “ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Network…☆55Updated 5 years ago
- Tensorflow implementation of Meta Adversarial Training for Adversarial Patch Attacks on Tiny ImageNet.☆25Updated 3 years ago
- Interval attacks (adversarial ML)☆21Updated 5 years ago
- Circumventing the defense in "Ensemble Adversarial Training: Attacks and Defenses"☆39Updated 6 years ago
- ☆83Updated last year
- Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"☆26Updated 2 years ago
- A general method for training cost-sensitive robust classifier☆21Updated 5 years ago
- ☆18Updated 5 years ago
- An (imperfect) implementation of wide resnets and Parseval regularization☆8Updated 4 years ago
- Certifying Geometric Robustness of Neural Networks☆15Updated last year
- A curated list of awesome resources regarding machine learning reliability.☆30Updated 3 years ago
- Implementation of our ICLR 2021 paper: Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples.☆11Updated 3 years ago
- Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019☆46Updated last year
- Unofficial implementation of the paper 'Adversarial Training for Free'☆21Updated 5 years ago
- ☆25Updated 5 years ago
- Codebase for the paper "Adversarial Attacks on Time Series"☆18Updated 5 years ago
- Research prototype of deletion efficient k-means algorithms☆23Updated 4 years ago
- Code for the paper "Weight Poisoning Attacks on Pre-trained Models" (ACL 2020)☆138Updated 3 years ago
- Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]☆31Updated 4 years ago
- Adversarial Examples: Attacks and Defenses for Deep Learning☆31Updated 6 years ago