网硕互联帮助中心ADR（智能体AI检测与响应）是一个面向AI智能体的企业安全系统。它帮助组织保护面向员工的智能体，如Cursor、Claude Code和Codex，以及面向客户的智能体，如AI客服助手。
ADR (Agentic AI Detection and Response) is an enterprise security system for AI agents. It helps organizations secure employee-facing agents such as Cursor, Claude Code, and Codex, as well as customer-facing agents such as AI support agents.
已经在 Uber 部署了
GitHub – uber/ADR: ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber. · GitHub
论文地址
[2605.17380] ADR: An Agentic Detection System for Enterprise Agentic AI Security
How ADR secures enterprise AI agents
ADR 通过四项互补能力来保障企业级 AI 智能体的安全：观察智能体活动、评估防御措施、检测威胁以及阻止不安全行为。
ADR secures enterprise AI agents through four complementary capabilities: observing agent activity, evaluating defenses, detecting threats, and preventing unsafe actions.
Repository layout
This repository contains the open-source ADR Sensor, ADR-Bench, and ADR Detector described in the paper. The offline ADR Explorer engine, which hardens ADR Detection through pre-deployment red teaming, is not included here.
| Sensor/ | ADR Observability | Collect and normalize agent telemetry from Claude Code, Cursor, Codex, opencode, Claude Desktop, and others |
| Detection/ | ADR Benchmark + Detection | Dual-agent detector, 133 MCP servers, 303 benchmark tasks, baselines, figure scripts |
| docs/REPRODUCIBILITY.md | Evaluation | Step-by-step workflow to reproduce benchmark detection and paper figures |
—
评论前必须登录！
注册