Lp Adversarial Examples using Projected Gradient Descent in PyTorch

Adversarial examples, slightly perturbed images causing mis-classification, have received considerable attention over the last few years. While many different adversarial attacks have been proposed, projected gradient descent (PGD) and its variants is widely spread for reliable evaluation or adversarial training. In this article, I want to present my implementation of PGD to generate L_∞, L₂, L₁ and L₀ adversarial examples. Besides using several iterations and multiple attempts, the worst-case adversarial example across all iterations …

adversarial attacks adversarial machine learning article attacks attention blog classification deep learning evaluation examples gradient images implementation python pytorch training variants