SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918528701956096 |
|---|---|
| author | Xin, Yuan Weng, Yixuan Zhu, Minjun Ling, Ying Qin, Chengwei Backes, Michael Zhang, Yue Yang, Linyi |
| author_facet | Xin, Yuan Weng, Yixuan Zhu, Minjun Ling, Ying Qin, Chengwei Backes, Michael Zhang, Yue Yang, Linyi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26506 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts Xin, Yuan Weng, Yixuan Zhu, Minjun Ling, Ying Qin, Chengwei Backes, Michael Zhang, Yue Yang, Linyi Computation and Language Cryptography and Security 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. |
| title | SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts |
| topic | Computation and Language Cryptography and Security |
| url | https://arxiv.org/abs/2604.26506 |