Reproduce “FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction” 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

Runqi Lin, Alasdair Paren, Suqin Yuan, Muyang Li, Philip Torr, Adel Bibi, Tongliang Liu

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.