Reproduce “Data-Efficient Backdoor Attacks on Code Models via Trigger-Neutralized Counterfactual Scoring” 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
Yu-Yu Lee, Ming-Feng Tsai, Tomohiro Morikawa, Chun-I Fan
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.