arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.26394cs.CRcs.AI
收藏

SecMate:基于三重上下文个性化多智能体网络安全故障排查

SecMate: Multi-Agent Adaptive Cybersecurity Troubleshooting with Tri-Context Personalization

Ben-Gurion University of the Negev(贝加尔-戈里昂大学)

Yair Meidan, Omri Haller, Yulia Moshan, Shahaf David, Dudu Mimran, Yuval Elovici, Asaf Shabtai

AI总结:

SecMate通过整合设备、用户和服务特定性,利用轻量级本地诊断工具和隐式技能推断,提升网络安全故障排查的准确性和用户满意度。

摘要:

近期大语言模型和智能体框架的发展使虚拟客户助理(VCAs)能够处理复杂支持任务。我们提出了SecMate,一种多智能体VCAs,整合了对话和设备层面的信号,提供设备特定性(通过轻量级本地诊断工具)、用户特定性(通过隐式技能推断和基于资料的故障排查)和服务特定性(通过主动、上下文感知推荐器)。在144名参与者和711次对话的受控研究中,设备层面证据将正确解决率从约50%提升到超过90%,逐步指导提高了愉悦度并减少了用户负担。推荐器达到了高相关性(MRR@1=0.75),参与者表现出强烈的意愿在成本低于人类基准的情况下替代人类IT支持。我们发布了完整的代码库和丰富的标注数据集,以支持对自适应VCAs的可重复研究。

英文摘要:

Recent advances in large language models and agentic frameworks have enabled virtual customer assistants (VCAs) for complex support. We present SecMate, a multi-agent VCA for cybersecurity troubleshooting that integrates device, user, and service specificity from conversational and device-level signals. Device specificity is provided by a lightweight local diagnostic utility, while user specificity relies on implicit proficiency inference and profile-aware troubleshooting. Service specificity is achieved through a proactive, context-aware recommender. We evaluate SecMate in a controlled study with 144 participants and 711 conversations. Device-level evidence increased correct resolutions from about 50% to over 90% relative to an LLM-only baseline, while step-by-step guidance improved pleasantness and reduced user burden. The recommender achieved high relevance (MRR@1=0.75), and participants showed strong willingness to substitute human IT support at costs well below human benchmarks. We release the full code base and a richly annotated dataset to support reproducible research on adaptive VCAs.

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。

↑