Reproduce “Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks” 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

Rongting Zhang, Martin Bertran, Sandeep Avula, Chia-Jung Lee, Vanessa Murdock

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