Convex-adversarial

Latest version: v0.4.4

Safety actively analyzes 613482 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

0.4

Notable changes:
+ Removed extraneous arguments that had no meaning (l1_eps, m, k)
+ Changed naming of arguments specifically labeled for L-infinity perturbations to allow for L2 perturbations
+ Added trained models in `models_scaled`. These are all cascaded models for MNIST and CIFAR at the epsilon levels described in the paper.
+ Added code for L2 perturbations in the input space.

This version is on PyPI under version 0.4 and works with PyTorch 0.4.

0.2

This version reproduces the results of [Provable defenses against adversarial examples via the convex outer adversarial polytope, by Eric Wong and J. Zico Kolter](https://arxiv.org/abs/1711.00851).

Links

Releases

Has known vulnerabilities

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.