FICHA · AUR

python-torchattacks

PyTorch implementation of adversarial attacks

  • Adversarial ML library
  • LIBRARY
  • Dependency only
official+codex · reviewed · Jun 3, 2026 description in en

Description

Adversarial examples can be generated against PyTorch models for robustness research and evaluation. Researchers and ML engineers can test classifiers against perturbation methods and compare defensive techniques. It is dual-use model-evaluation tooling and should be used on models and data you are authorized to test.

Permissions

Permissions not analysed for this source yet.