Reproduce “Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding” 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, Arnout Van Messem, Wesley De Neve
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.