CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks

TL;DR

CoopGuard is a multi-agent framework that enhances LLM security against evolving multi-round adversarial attacks by maintaining an adaptive defense state and coordinating specialized agents.

Contribution

It introduces a novel stateful multi-round defense framework with specialized agents and a new benchmark for evaluating evolving threats.

Findings

CoopGuard reduces attack success rate by 78.9% compared to existing defenses.

It improves deceptive rate by 186% and reduces attack efficiency by 167.9%.

The EMRA benchmark includes 5,200 adversarial samples across 8 attack types.

Abstract

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.