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 2605.30604cs.CRcs.AIcs.CLcs.IR
收藏

面向受监管网络安全运营的组织范围LLM代理运行时架构

An Organization-Scoped LLM Agent Runtime Architecture for Regulated Cybersecurity Operations

Innov-Acts Ltd(Innov-Acts有限公司);Dept. of Digital Systems University of Piraeus(数字系统系希腊比雷埃克斯大学);Harokopio University(哈罗基奥大学);Dept. of Informatics and Telematics(信息学与电信系)

George Fatouros, Georgios Makridis, George Kousiouris, John Soldatos, Dimosthenis Kyriazis

AI总结:

提出一种组织范围的LLM代理运行时架构,通过类型化安全上下文、运行时核心、专业子代理、受控工具适配层和分层人机回环,实现检索、工具调用、内存、发现、报告和审计的全局强制,并保持模型无关和本地部署。

摘要:

受监管的网络安全工作流缺乏一个运行时基础,该基础能够在检索、工具调用、内存、发现、报告和审计中强制执行组织范围,同时保持模型无关和本地可部署。近期的大语言模型(LLM)代理系统在孤立的网络安全任务上报告了强劲结果,但它们本身并未为受监管的安全运营中心(SOC)和合规工作流定义一个可审计的平台架构,在这些工作流中,单个分析师可能触发约束整个组织的行动,并且运行时必须与现有的SIEM/XDR堆栈集成,作为上下文和告警驱动触发器的主要来源,而不是作为独立的分析层运行。本文提出了一种面向金融网络安全的组织范围LLM代理运行时架构。其贡献是一个类型化的安全上下文,该上下文在每个入口点创建,包括作为一等触发器摄入的SIEM/XDR通知,并在每个组件边界强制执行,结合共享的运行时核心、逻辑专业子代理、受控工具适配层(在统一策略和审计下暴露SIEM/XDR查询、丰富和响应原语)、带有证据引用的结构化发现、分层人机回环(HITL)门控以及仅追加审计。模型上下文协议(MCP)、扩展遥测、用于渗透测试的数字孪生、图检索和联邦知识共享被视为可选的扩展路径,而非强制性的运行时假设。我们描述了一个可实现的切片作为架构的可测试性表面,并提出了一个可证伪的评估计划,包含用于架构就绪性、安全策略执行、证据可追溯性、输出质量和运营可观测性的度量级通过标准。

英文摘要:

Regulated cybersecurity workflows lack a runtime substrate that enforces organization-level scope across retrieval, tool calls, memory, findings, reports, and audit while remaining model-agnostic and locally deployable. Recent large language model (LLM) agent systems report strong results on isolated cybersecurity tasks, yet they do not by themselves define an auditable platform architecture for regulated security operations centre (SOC) and compliance workflows, where a single analyst may trigger actions that bind the organization, and where the runtime must integrate with existing SIEM/XDR stacks as a primary source of context and alert-driven triggers rather than operate as a standalone analytical layer. This paper proposes an organization-scoped LLM agent runtime architecture for financial cybersecurity. The contribution is a typed Security Context that is created at every entry point, including SIEM/XDR notifications ingested as first-class triggers, and enforced at every component boundary, combined with a shared Runtime Core, logical specialist subagents, a governed Tool Adapter Layer exposing SIEM/XDR query, enrichment, and response primitives under uniform policy and audit, structured findings with evidence references, tiered human-in-the-loop (HITL) gates, and append-only audit. Model Context Protocol (MCP), extended telemetry, digital twins for pentesting, graph retrieval, and federated knowledge sharing are treated as optional extension paths rather than mandatory runtime assumptions. We describe an implementable slice as the architecture's testability surface, and we propose a falsifiable evaluation plan with metric-level pass criteria for architecture readiness, security-policy enforcement, evidence traceability, output quality, and operational observability.

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。

↑