Torchattacks: A PyTorch Repository for Adversarial Attacks

TL;DR

Torchattacks is a PyTorch library that provides tools for generating adversarial examples and testing the robustness of deep learning models against such attacks.

Contribution

It introduces a comprehensive PyTorch-based library for adversarial attacks, facilitating research and evaluation of model robustness.

Findings

Enables easy generation of adversarial examples

Supports multiple attack algorithms

Helps verify model robustness

Abstract

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.