Paper

Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review

Unreadunread

AI summary

arXiv:2606. 12716v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) into scientific peer-review workflows introduces novel and significant risks for adversarial manipulation, especially given the multimodal nature of scientific papers where figures, not just text, convey core evidence.

Reading status

Priority

About this paper

Authors: Xinyu Zhao, Rana Muhammad Shahroz Khan, Zhen Xu, Zhen Tan, Tianlong Chen
Released: 2026-06-12 (27d ago)
Topic: Related to current project
Relation to my work: Read next because Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, eval, rate, does, full, language, model. Source: arxiv cs.CL (NLP).
arXiv: 2606.12716

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.