Detecting Shadow AI: Unsanctioned LLM Agents on Enterprise Endpoints: A Taxonomy, an Open Detector and a Controlled Evaluation
cs.AI, cs.CR
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/FoxIO-LLC/ja4
Project page: https://microsoft.github.io/zerotrustassessment/docs/workshop-guidance/AI/AI_176
Terminology
Sources
- From Frontier to Shadow AI: A Simmering Threat to Assurance and Security in Critical Infrastructure
- Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity
- Governing Bring Your Own AI: A Parameterized Maturity Model
- Visibility into AI Agents
- Infrastructure for AI Agents
- Harness Engineering for Agentic AI Coding Tools: An Exploratory Study
- Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
- Digital Forensic Investigation of the ChatGPT Windows Application
- Whisper Leak: a side-channel attack on Large Language Models
- The Impact of AI on Developer Productivity: Evidence from GitHub Copilot
- A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services
- MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
- Agentic Much? Adoption of Coding Agents on GitHub
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Authenticated Delegation and Authorized AI Agents
- How are AI agents used? Evidence from 177,000 MCP tools
- OpenHands: An Open Platform for AI Software Developers as Generalist Agents
- On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
- ReAct: Synergizing Reasoning and Acting in Language Models
- Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of Privacy Risks in LLM Agent Interactions
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents