# SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts

arXiv: https://arxiv.org/abs/2604.26506 · HTML: https://mlsanity.com/paper/2604.26506/

## Key facts

- Cited by 4 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 24 of its 40 references that are in the map.
- First posted on arXiv 29 Apr 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, 24 of 24)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Emergent Tool Use From Multi-Agent Autocurricula](https://mlsanity.com/paper/1909.07528/) (2019)
- [SecAlign: Defending Against Prompt Injection with Preference Optimization](https://mlsanity.com/paper/2410.05451/) (2024)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications](https://mlsanity.com/paper/1804.09635/) (2018)
- [MARG: Multi-Agent Review Generation for Scientific Papers](https://mlsanity.com/paper/2401.04259/) (2024)
- [Large Language Models for Automated Open-domain Scientific Hypotheses Discovery](https://mlsanity.com/paper/2309.02726/) (2023)
- [DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process](https://mlsanity.com/paper/2503.08569/) (2025)
- [SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning](https://mlsanity.com/paper/2409.05556/) (2024)
- [IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models](https://mlsanity.com/paper/1705.10513/) (2017)
- [The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates](https://mlsanity.com/paper/2405.02150/) (2024)
- [Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas](https://mlsanity.com/paper/2410.14255/) (2024)
- [Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review](https://mlsanity.com/paper/2412.01708/) (2024)
- [Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions](https://mlsanity.com/paper/2406.05688/) (2024)
- [Automated Statistical Model Discovery with Language Models](https://mlsanity.com/paper/2402.17879/) (2024)
- [Defense Against Prompt Injection Attack by Leveraging Attack Techniques](https://mlsanity.com/paper/2411.00459/) (2024)
- [Can large language models replace humans in the systematic review process? Evaluating GPT-4's efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages](https://mlsanity.com/paper/2310.17526/) (2023)
- [Summarizing Multiple Documents with Conversational Structure for Meta-Review Generation](https://mlsanity.com/paper/2305.01498/) (2023)
- [CiteBench: A benchmark for Scientific Citation Text Generation](https://mlsanity.com/paper/2212.09577/) (2022)
- [Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks](https://mlsanity.com/paper/2506.11113/) (2025)
- [Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications](https://mlsanity.com/paper/2509.10248/) (2025)
- [CARE: Collaborative AI-Assisted Reading Environment](https://mlsanity.com/paper/2302.12611/) (2023)
- [AEGIS : Automated Co-Evolutionary Framework for Guarding Prompt Injections Schema](https://mlsanity.com/paper/2509.00088/) (2025)

## Built on by (most cited first, 4 of 4)

- [MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility](https://mlsanity.com/paper/2605.16616/) (2026)
- [The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing](https://mlsanity.com/paper/2609.07713/) (2026)
- [AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists](https://mlsanity.com/paper/2605.21481/) (2026)
- [More Criticism Does Not Make a Better Review: EquiReview-R](https://mlsanity.com/paper/2609.03943/) (2026)

## Abstract (arXiv)

As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in submissions to manipulate outcomes, poses a critical threat to scholarly integrity. We propose SafeReview, a co-evolutionary adversarial training framework for defending LLM-based peer review systems against such attacks. SafeReview jointly trains a Generator model to create sophisticated attack prompts and a Defender model to preserve review integrity under adversarial manipulation. The Generator is optimized to produce increasingly effective prompt injections, while the Defender is strengthened through preference-based training to maintain consistent reviews between clean and attacked submissions. Experimental results show that SafeReview improves robustness against adaptive prompt injection attacks, better preserves paper ranking under attack, and generalizes across attacker architectures compared with static defenses. These results demonstrate the potential of co-evolutionary training as a foundation for securing LLM-assisted peer review.