Reproduce “Regional Image Perturbation Reduces $L_p$ Norms of Adversarial Examples While Maintaining Model-to-model Transferability” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Utku Ozbulak, Jonathan Peck, Wesley De Neve, Bart Goossens, Yvan Saeys, Arnout Van Messem
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.