Torchattacks: A PyTorch Repository for Adversarial Attacks
arXiv:2010.01950v3271 citationsHas Code
Originality Synthesis-oriented
AI Analysis
This provides a useful tool for researchers and practitioners in adversarial machine learning, but it is incremental as it repackages existing methods into a PyTorch framework.
The authors tackled the need for a standardized PyTorch library for adversarial attacks by developing Torchattacks, which provides tools to generate adversarial examples and verify model robustness, with the code publicly available on GitHub.
Torchattacks is a PyTorch library that contains adversarial attacks to generate adversarial examples and to verify the robustness of deep learning models. The code can be found at https://github.com/Harry24k/adversarial-attacks-pytorch.