FICHA · AUR

python-eagerpy-git

Toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, Keras,

  • Adversarial machine-learning toolbox
  • LIBRARY
  • AI
  • SECURITY
  • Dependency only
official+codex · reviewed · Jun 3, 2026 description in en

Description

Neural-network robustness can be tested with adversarial examples across PyTorch, TensorFlow, Keras, and related stacks. This toolbox is for authorized research, evaluation, and model-hardening work. Generated inputs are meant to expose model weaknesses and should not be used to bypass systems without permission.

Permissions

Permissions not analysed for this source yet.