有益于故障：测量多轮、多语言LLM代理中的非法协助
Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
AI总结：
本文提出STING框架，用于评估多轮多语言LLM代理在执行非法任务时的协助能力，发现低资源语言中攻击成功率不一致，提供实际部署中的压力测试方法。
摘要：
基于工具和记忆的LLM代理通过执行现实世界工作流。这些功能使恶意对手也能利用这些代理执行复杂的恶意场景。现有代理恶意使用基准测试主要测试单提示指令，留下测量代理在多轮中帮助执行有害或非法任务的空白。我们引入STING（序列测试非法N步目标执行），一种自动红队框架，构建基于良性角色的逐步非法计划，并通过适应性后续问题迭代探测目标代理，使用判断代理跟踪阶段完成。我们进一步引入分析框架，将多轮红队测试建模为首次越狱时间随机变量，使分析工具如发现曲线、攻击语言的危险比率归因以及新指标：受限均值越狱发现。在AgentHarm场景中，STING的非法任务完成率显著高于单轮提示和适应于工具使用代理的多轮基线。在六个非英语设置的多语言评估中，发现攻击成功率和非法任务完成率在低资源语言中不一致，与常见聊天机器人发现不同。总体而言，STING提供了一种评估和压力测试代理恶意使用在现实部署环境中的实用方法，其中交互本质上是多轮且经常多语言的。
英文摘要：
LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test single-prompt instructions, leaving a gap in measuring how agents end up helping with harmful or illegal tasks over multiple turns. We introduce STING (Sequential Testing of Illicit N-step Goal execution), an automated red-teaming framework that constructs a step-by-step illicit plan grounded in a benign persona and iteratively probes a target agent with adaptive follow-ups, using judge agents to track phase completion. We further introduce an analysis framework that models multi-turn red-teaming as a time-to-first-jailbreak random variable, enabling analysis tools like discovery curves, hazard-ratio attribution by attack language, and a new metric: Restricted Mean Jailbreak Discovery. Across AgentHarm scenarios, STING yields substantially higher illicit-task completion than single-turn prompting and chat-oriented multi-turn baselines adapted to tool-using agents. In multilingual evaluations across six non-English settings, we find that attack success and illicit-task completion do not consistently increase in lower-resource languages, diverging from common chatbot findings. Overall, STING provides a practical way to evaluate and stress-test agent misuse in realistic deployment settings, where interactions are inherently multi-turn and often multilingual.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
