Refactor unit tests for FGSM, BIM and PGD attacks

Trusted-AI / adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

MIT License

4.88k stars 1.17k forks source link

Closed beat-buesser closed 4 years ago

beat-buesser commented 4 years ago

Refactor unit tests for FGSM, BIM and PGD attacks.

reuse test codes across frameworks and attack modules
similar models (e.g. ART's standard neural networks for testing) across different frameworks should test against the same expected values.

beat-buesser commented 4 years ago

@killianlevacher Thank you very much for working on this issue!