Skip to content
Search
paperMay 2026Unreviewed

ADR: An Agentic Detection System for Enterprise Agentic AI Security

Chenning Li, Pan Hu, Justin Xu, Baris Ozbas, Olivia Liu, Caroline Van, Manxue Li, Wei Zhou, Mohammad Alizadeh, Pengyu Zhang, KK Sriramadhesikan, Ming Zhang

View resourcePDF

Abstract

We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Context Protocol (MCP). We identify three persistent challenges in this domain: (1) limited observability -- existing Endpoint Detection and Response (EDR) tools see file writes but not the agent reasoning, prompts, or causal chains linking intent to execution; (2) insufficient robustness -- static defenses constrained by

Categories

Agentic Threats

Cite

@misc{li2026adr,
  title = {{ADR: An Agentic Detection System for Enterprise Agentic AI Security}},
  author = {Chenning Li and Pan Hu and Justin Xu and Baris Ozbas and Olivia Liu and Caroline Van and Manxue Li and Wei Zhou and Mohammad Alizadeh and Pengyu Zhang and KK Sriramadhesikan and Ming Zhang},
  year = {2026},
  month = may,
  eprint = {2605.17380},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.17380}
}