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.

翻译：将大语言模型（LLMs）和多模态大语言模型（MLLMs）集成到科学同行评审流程中，引入了新颖且重大的对抗性操纵风险——尤其是考虑到科学论文的多模态特性（图表与文本共同传递核心证据）。当前研究的显著缺陷在于：针对AI同行评审的鲁棒性研究几乎完全局限于文本单模态。此外，该问题与标准越狱攻击存在本质差异——同行评审攻击旨在诱发领域特定的定向失效（如"抬高评分"），而非违反通用安全策略，且缺乏实用防御手段。为此，我们提出PaperGuard——首个系统化评估与防御跨模态领域特异性AI评审攻击的综合性基准框架。该框架基于三大支柱构建：（1）覆盖多学科领域的多模态同行评审新数据集；（2）统一攻击工具集，包含针对文本（GCG）和图表（PGD）的黑盒提示注入与白盒扰动攻击；（3）基于学术论文长上下文挑战设计的实用防御机制，通过分块嵌入搜索高效定位并消除有害指令。我们在多个前沿模型上的大量实验证实，AI评审者普遍存在脆弱性。PaperGuard为开创可信、抗攻击的AI辅助学术评审奠定了基准基础、协议规范与可操作防御方案。