Artificial Intelligence (AI) agents can now orchestrate cyberattacks. This development is already increasing the speed and scale of cyber attacks, decreasing attack costs, and improving the operational autonomy of cyber capabilities. To defend against these emerging threats, actors must first develop the capability to detect them. This report frames the offensive cyber agent detection challenge by outlining the coming detection gap between offensive cyber agents and traditional cyber capabilities; introducing detection-in-depth, a strategic framework to guide policymakers and defenders responding to this detection gap; and presents five actionable detection mechanisms to support policymakers, industry, and defenders when putting this strategic framework into practice. These include (1) Agent Identifiers for Critical Infrastructure,(2) Agent Honeypots; (3) AI-Automated Alert Analysis and Triage: systems that use AI to filter, prioritize, and interpret the growing volume of detection signals expected from autonomous cyber operations; (4) An Agentic Security Alert Standard: A reporting standard model that providers can use to communicate agentic threats, improving the speed, consistency, and actionability of reports; (5) An Agentic Cybersecurity Exchange (ACE): an institution modeled on the Global Signal Exchange that brings together model and cloud providers to detect offensive cyber agent threats at their origin point and coordinate ecosystem-wide agentic threat disruption.

翻译：人工智能代理现可协调发起网络攻击。这一发展正在加速网络攻击的速度与规模、降低攻击成本，并提升网络能力的操作自主性。为防御此类新兴威胁，各方需首先具备检测能力。本报告通过三方面框架化攻击性网络代理检测挑战：概述攻击性网络代理与传统网络能力之间存在的检测差距；引入"深度检测"战略框架以指导决策者与防御者应对该检测差距；提出五项可落地检测机制，支持决策者、行业和防御者将战略框架付诸实践。这些机制包括：(1)关键基础设施代理标识符；(2)代理蜜罐；(3)人工智能自动化告警分析与分类——利用人工智能对自主网络操作预期产生的海量检测信号进行过滤、优先级排序和解读的系统；(4)代理安全告警标准——一种报告标准模型，供提供商用于传达代理威胁，提升报告速度、一致性与可操作性；(5)代理网络安全交易所——以全球信号交易所为蓝本建立的机构，聚集模型和云服务商在攻击源头检测攻击性网络代理威胁，并协调全生态圈的代理威胁阻断行动。