Reproduce “Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems” 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
Sergey Berezin, Reza Farahbakhsh, Noel Crespi
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.