ai-peer-review

Tag

Cards List
#ai-peer-review

No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions

arXiv cs.CL · 4d ago Cached

This paper demonstrates that AI peer reviewers can be manipulated by modifying only presentation-level content (such as abstract, framing, and narrative) without changing any scientific evidence, achieving a 75.1% attack success rate. The authors introduce adversarial repackaging, a closed-loop attack that exploits AI reviewers' tendency to be impressed rather than convinced, and release a benchmark for testing robustness.

0 favorites 0 likes
← Back to home

Submit Feedback