Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review
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. This creates a significant gap: current robustness studies on AI peer-review are overwhelmingly text-only. Moreover, the problem is distinct from standard jailbreaking, as a peer-review attack seeks to induce a domain-specific, targeted failure (e.g., "inflate this score") rather than a general safety policy violation, for which no practical defenses exist. To address this, we introduce PaperGuard, the first comprehensive benchmark designed to systematically evaluate and defend AI-generated peer-review against these domain-specific, cross-modal attacks. Our framework is built on three pillars: (1) a new multimodal peer-review dataset spanning multiple scientific domains; (2) a unified suite of attacks, including black-box prompt injections and white-box perturbations, specifically designed to target both text (GCG) and figures (PGD); and (3) a practical defense, motivated by the long-context challenge of academic papers, that uses chunk-based embedding search to efficiently localize and mitigate harmful instructions. Our extensive experiments, conducted across state-of-the-art models, confirm that AI reviewers are pervasively vulnerable. PaperGuard establishes the foundational benchmark, protocols, and actionable defense necessary to pioneer trustworthy, attack-resilient AI-assisted scholarly reviewing.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Security Matters: A Survey on Adversarial Machine Learning
Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-t…
BIG-bench Machine LearningDeep LearningSurveyGoal-Oriented Prompt Attack and Safety Evaluation for LLMs
Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There ar…
Is a Picture Worth Ten Thousand Words in a Review Dataset?
While textual reviews have become prominent in many recommendation-based systems, automated frameworks to provide relevant visual cues against text reviews where pictures are not available is a new form of task confronte…
TAGGrey-box Adversarial Attack And Defence For Sentiment Classification
We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in…
Adversarial AttackClassificationGeneral ClassificationSentiment Analysis+1Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective
As Large Language Models (LLMs) become an important way of information seeking, there have been increasing concerns about the unethical content LLMs may generate. In this paper, we conduct a rigorous evaluation of LLMs' …