# No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions arXiv: https://arxiv.org/abs/2606.13044 ยท HTML: https://mlsanity.com/paper/2606.13044/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security. - Builds on 27 of its 41 references that are in the map. - First posted on arXiv 11 Jun 2026. ## Placed in - LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/) ## Builds on (most cited first, 27 of 27) - [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023) - [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024) - [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019) - [Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews](https://mlsanity.com/paper/2403.07183/) (2024) - [Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment](https://mlsanity.com/paper/2402.14016/) (2024) - [LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models](https://mlsanity.com/paper/2307.07889/) (2023) - [The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates](https://mlsanity.com/paper/2405.02150/) (2024) - [OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews](https://mlsanity.com/paper/2412.11948/) (2024) - [Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review](https://mlsanity.com/paper/2412.01708/) (2024) - [LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge](https://mlsanity.com/paper/2506.09443/) (2025) - [Position: The AI Conference Peer Review Crisis Demands Author Feedback and Reviewer Rewards](https://mlsanity.com/paper/2505.04966/) (2025) - [TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review](https://mlsanity.com/paper/2506.07642/) (2025) - [Mind the Blind Spots: A Focus-Level Evaluation Framework for LLM Reviews](https://mlsanity.com/paper/2502.17086/) (2025) - [ReviewRL: Towards Automated Scientific Review with RL](https://mlsanity.com/paper/2508.10308/) (2025) - [When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review](https://mlsanity.com/paper/2509.09912/) (2025) - [LitLLMs, LLMs for Literature Review: Are we there yet?](https://mlsanity.com/paper/2412.15249/) (2024) - [Stop Automating Peer Review Without Rigorous Evaluation](https://mlsanity.com/paper/2605.03202/) (2026) - [Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews](https://mlsanity.com/paper/2509.13400/) (2025) - [Paper Copilot: Tracking the Evolution of Peer Review in AI Conferences](https://mlsanity.com/paper/2510.13201/) (2025) - [LLM-REVal: Can We Trust LLM Reviewers Yet?](https://mlsanity.com/paper/2510.12367/) (2025) - [BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?](https://mlsanity.com/paper/2510.18003/) (2025) - [Paraphrasing Adversarial Attack on LLM-as-a-Reviewer](https://mlsanity.com/paper/2601.06884/) (2026) - [Stop DDoS Attacking the Research Community with AI-Generated Survey Papers](https://mlsanity.com/paper/2510.09686/) (2025) - [Pre-review to Peer review: Pitfalls of Automating Reviews using Large Language Models](https://mlsanity.com/paper/2512.22145/) (2025) - [Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future](https://mlsanity.com/paper/2604.27924/) (2026) - ["Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers](https://mlsanity.com/paper/2511.01287/) (2025) - [Exploring the Effects of Alignment on Numerical Bias in Large Language Models](https://mlsanity.com/paper/2601.16444/) (2026) ## Built on by (most cited first, 2 of 2) - [How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review](https://mlsanity.com/paper/2608.08975/) (2026) - [The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing](https://mlsanity.com/paper/2609.07713/) (2026) ## Abstract (arXiv) 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 injection, and no changes to methods, experiments, figures, equations, proofs, or numerical results. The attacker modifies only presentation-level content, such as the abstract, contribution framing, related work, discussion, and narrative structure. We introduce adversarial repackaging: a closed-loop attack that uses AI-reviewer feedback to search for presentation-level revisions while keeping the scientific evidence fixed. Across three mainstream AI reviewers, adversarial repackaging achieves a 75.1% attack success rate and a mean score gain of +1.21/10. The effect is not explained by ordinary prose polishing. We also reveal that strategies that change how the reviewer interprets the paper, such as related-work repositioning and analytical discussion expansion, substantially outperform surface edits such as local polishing, table formatting, and algorithm boxes. Our analysis reveals two deeper structural failure modes. First, AI reviewers are easier to impress than to convince: highlighting strengths reliably increases perceived merit, while attempts to dissolve weaknesses frequently backfire. Second, AI reviewers can confuse the appearance of addressing a limitation with actually resolving it, allowing unchanged evidence to be reinterpreted as stronger scientific contribution. These results show that the deployment risk is not only malicious hidden instructions, but the emergence of paper presentation itself as an optimization surface. We release a contamination-free rolling benchmark and attack framework for testing whether AI reviewers remain anchored to scientific content under presentation-only edits.