Skip to content
AI News HubLIVE
Original source2 min read

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

Summary

Researchers introduce PaperGuard, the first benchmark for systematically evaluating and defending AI-generated peer review against domain-specific, cross-modal attacks, revealing pervasive vulnerabilities in state-of-the-art models.

SourcearXiv Computational LinguisticsAuthor: Xinyu Zhao, Rana Muhammad Shahroz Khan, Zhen Xu, Zhen Tan, Tianlong Chen
Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.12716] Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review

[Submitted on 10 Jun 2026]

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

View a PDF of the paper titled Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review, by Xinyu Zhao and 4 other authors

View PDF HTML (experimental)

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. 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.

Comments: Accepted to ICML 2026, Project Page: this https URL

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2606.12716 [cs.CL]

(or arXiv:2606.12716v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.12716

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xinyu Zhao [view email] [v1] Wed, 10 Jun 2026 22:06:35 UTC (2,808 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review, by Xinyu Zhao and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • PaperGuard is the first comprehensive benchmark for multimodal peer-review attacks and defenses.
  • Attacks include black-box prompt injections and white-box perturbations targeting text (GCG) and figures (PGD).
  • A practical defense uses chunk-based embedding search to localize and mitigate harmful instructions.
  • Experiments show AI reviewers are pervasively vulnerable.

Highlights and analysis are generated automatically and may contain errors. Check the original source.