Abstract:As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial prompts -- adversarial instructions embedded in submissions to manipulate outcomes -- emerges as a critical threat to scholarly integrity. To counter this, we propose a novel adversarial framework where a Generator model, trained to create sophisticated attack prompts, is jointly optimized with a Defender model tasked with their detection. This system is trained using a loss function inspired by Information Retrieval Generative Adversarial Networks, which fosters a dynamic co-evolution between the two models, forcing the Defender to develop robust capabilities against continuously improving attack strategies. The resulting framework demonstrates significantly enhanced resilience to novel and evolving threats compared to static defenses, thereby establishing a critical foundation for securing the integrity of peer review.
| Comments: | 10 pages, 3 figures, 9 tables |
| Subjects: | Computation and Language (cs.CL); Cryptography and Security (cs.CR) |
| Cite as: | arXiv:2604.26506 [cs.CL] |
| (or arXiv:2604.26506v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2604.26506 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuan Xin [view email]
[v1]
Wed, 29 Apr 2026 10:11:12 UTC (1,235 KB)