CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914447490023424 |
|---|---|
| author | Li, Siyuan Liu, Zehao Lin, Xi Mao, Qinghua Chen, Yuliang Li, Haoyu Wu, Jun Li, Jianhua Su, Xiu |
| author_facet | Li, Siyuan Liu, Zehao Lin, Xi Mao, Qinghua Chen, Yuliang Li, Haoyu Wu, Jun Li, Jianhua Su, Xiu |
| contents | As Large Language Models (LLMs) are increasingly deployed in complex applications, their vulnerability to adversarial attacks raises urgent safety concerns, especially those evolving over multi-round interactions. Existing defenses are largely reactive and struggle to adapt as adversaries refine strategies across rounds. In this work, we propose CoopGuard , a stateful multi-round LLM defense framework based on cooperative agents that maintains and updates an internal defense state to counter evolving attacks. It employs three specialized agents (Deferring Agent, Tempting Agent, and Forensic Agent) for complementary round-level strategies, coordinated by System Agent, which conditions decisions on the evolving defense state (interaction history) and orchestrates agents over time. To evaluate evolving threats, we introduce the EMRA benchmark with 5,200 adversarial samples across 8 attack types, simulating progressively LLM multi-round attacks. Experiments show that CoopGuard reduces attack success rate by 78.9% over state-of-the-art defenses, while improving deceptive rate by 186% and reducing attack efficiency by 167.9%, offering a more comprehensive assessment of multi-round defense. These results demonstrate that CoopGuard provides robust protection for LLMs in multi-round adversarial scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04060 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks Li, Siyuan Liu, Zehao Lin, Xi Mao, Qinghua Chen, Yuliang Li, Haoyu Wu, Jun Li, Jianhua Su, Xiu Cryptography and Security Artificial Intelligence As Large Language Models (LLMs) are increasingly deployed in complex applications, their vulnerability to adversarial attacks raises urgent safety concerns, especially those evolving over multi-round interactions. Existing defenses are largely reactive and struggle to adapt as adversaries refine strategies across rounds. In this work, we propose CoopGuard , a stateful multi-round LLM defense framework based on cooperative agents that maintains and updates an internal defense state to counter evolving attacks. It employs three specialized agents (Deferring Agent, Tempting Agent, and Forensic Agent) for complementary round-level strategies, coordinated by System Agent, which conditions decisions on the evolving defense state (interaction history) and orchestrates agents over time. To evaluate evolving threats, we introduce the EMRA benchmark with 5,200 adversarial samples across 8 attack types, simulating progressively LLM multi-round attacks. Experiments show that CoopGuard reduces attack success rate by 78.9% over state-of-the-art defenses, while improving deceptive rate by 186% and reducing attack efficiency by 167.9%, offering a more comprehensive assessment of multi-round defense. These results demonstrate that CoopGuard provides robust protection for LLMs in multi-round adversarial scenarios. |
| title | CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2604.04060 |