Reproduce “Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing” 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

Dongliang Guo, Mengxuan Hu, Zihan Guan, Junfeng Guo, Thomas Hartvigsen, Sheng Li

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