Reproduce “SAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors” 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
Yutong Ke, Yansu Wang, Zeyu Zhang, Xihao Guo, Chongwen Zhao, Kaizhu Huang
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.