PulseAugur
EN
LIVE 13:23:26

AI Peer Review Vulnerable to Presentation-Only Attacks

By PulseAugur Editorial · [8 sources] ·

Recent research highlights significant vulnerabilities in AI-assisted scientific peer review systems. Studies demonstrate that AI reviewers can be manipulated through presentation-only revisions, such as altering abstracts or framing, without changing the core scientific content. These attacks can lead to inflated scores and increased acceptance rates, raising concerns that authors might optimize for AI judgment over scientific merit. Furthermore, multimodal AI reviewers are susceptible to attacks targeting figures and text, necessitating robust defenses and careful human oversight to maintain the integrity of the peer-review process. AI

IMPACT Highlights the need for robust AI systems in scientific evaluation to prevent manipulation and ensure integrity.

RANK_REASON Multiple research papers detailing vulnerabilities and potential defenses in AI-assisted scientific peer review.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 8 sources. How we write summaries →

COVERAGE [8]

  1. arXiv cs.CL TIER_1 English(EN) · Xu Yang, Zhizhou Sha, Junbo Li, Jian Yu, Yifan Sun, Matthew Zhao, Jinrui Fang, Xinyue Guo, Yining Wu, Xu Hu, Yifu Luo, Qiang Liu, Zhangyang Wang ·

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

    arXiv:2606.13044v1 Announce Type: new Abstract: As AI-generated reviews move from experimental tools into peer-review infrastructure, most robustness concerns have focused on explicit attacks such as hidden instructions and prompt injection. We study a harder and more policy-rele…

  2. arXiv cs.CL TIER_1 English(EN) · 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

    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 scienti…

  3. arXiv cs.CL TIER_1 English(EN) · Haishuo Fang, Yue Feng, Iryna Gurevych ·

    From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent

    arXiv:2606.13349v1 Announce Type: new Abstract: Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews supported by concrete evidence. We argue that a key limitation is the lac…

  4. Hugging Face Daily Papers TIER_1 English(EN) ·

    From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent

    Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews supported by concrete evidence. We argue that a key limitation is the lack of flexibility to proactively investigate susp…

  5. arXiv cs.CL TIER_1 English(EN) · Iryna Gurevych ·

    From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent

    Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews supported by concrete evidence. We argue that a key limitation is the lack of flexibility to proactively investigate susp…

  6. arXiv cs.CL TIER_1 English(EN) · Zhangyang Wang ·

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

    As AI-generated reviews move from experimental tools into peer-review infrastructure, most robustness concerns have focused on explicit attacks such as hidden instructions and prompt injection. We study a harder and more policy-relevant failure mode: no hidden text, no prompt inj…

  7. arXiv cs.AI TIER_1 English(EN) · Qiyao Wei, Samuel Holt, Jing Yang, Markus Wulfmeier, Mihaela van der Schaar ·

    Position: The ML Community Must Build an AI-Augmented Peer-Review Ecosystem

    arXiv:2506.08134v4 Announce Type: replace Abstract: Peer review, the bedrock of scientific advancement in machine learning (ML), is strained by a crisis of scale. Exponential growth in manuscript submissions to premier ML venues such as NeurIPS, ICML, and ICLR is outpacing the fi…

  8. arXiv cs.AI TIER_1 English(EN) · Lin Li, Qi Zhang, Xander Davies, Jianing Qiu, Yarin Gal ·

    Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community

    arXiv:2606.10159v1 Announce Type: cross Abstract: AI is increasingly used to support scientific peer review, from manuscript screening, reviewer assistance to editorial triage. Although such systems promise to reduce reviewer burden and accelerate publication, their robustness to…

RELATED ENTITIES

RELATED TOPICS