Home

torchattack - A curated list of adversarial attacks in PyTorch, with a focus on transferable black-box attacks.

pip install torchattack

Highlights

• 🛡️ A curated collection of adversarial attacks implemented in PyTorch.
• 🔍 Focuses on gradient-based transferable black-box attacks.
• 📦 Easily load pretrained models from torchvision or timm using AttackModel.
• 🔄 Simple interface to initialize attacks with create_attack.
• 🔧 Extensively typed for better code quality and safety.
• 📊 Tooling for fooling rate metrics and model evaluation in eval.
• 🔁 Numerous attacks reimplemented for readability and efficiency (TGR, VDC, etc.).

Next Steps

• Usage

  ---

  Learn how to use abstractions of pretrained victim models, attack creations, and evaluations.

  Usage

• Attacks

  ---

  Explore the comprehensive list of adversarial attacks available in torchattack.

  Attacks

• Development

  ---

  On how to install dependencies, run tests, and build documentation.

  Development

License

torchattack is licensed under the MIT License.