# Signals in the Noise: Open Source Intelligence (OSINT) for AI Loss of Control Detection

arXiv: https://arxiv.org/abs/2606.20610 · HTML: https://mlsanity.com/paper/2606.20610/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 92 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 27 of 27)

- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [An Overview of Catastrophic AI Risks](https://mlsanity.com/paper/2306.12001/) (2023)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)
- [Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation](https://mlsanity.com/paper/2510.11977/) (2025)
- [Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development](https://mlsanity.com/paper/2501.16946/) (2025)
- [Security of AI Agents](https://mlsanity.com/paper/2406.08689/) (2024)
- [AgentSight: System-Level Observability for AI Agents Using eBPF](https://mlsanity.com/paper/2508.02736/) (2025)
- [Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language](https://mlsanity.com/paper/2507.03409/) (2025)
- [RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents](https://mlsanity.com/paper/2504.18565/) (2025)
- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [A Safety and Security Framework for Real-World Agentic Systems](https://mlsanity.com/paper/2511.21990/) (2025)
- [The Term 'Agent' Has Been Diluted Beyond Utility and Requires Redefinition](https://mlsanity.com/paper/2508.05338/) (2025)
- [OpsAgent: An Evolving Multi-agent System for Incident Management in Microservices](https://mlsanity.com/paper/2510.24145/) (2025)
- [Towards an AI-Enhanced Cyber Threat Intelligence Processing Pipeline](https://mlsanity.com/paper/2403.03265/) (2024)
- [Securing Agentic AI Systems -- A Multilayer Security Framework](https://mlsanity.com/paper/2512.18043/) (2025)
- [Measuring What AI Systems Might Do: Towards A Measurement Science in AI](https://mlsanity.com/paper/2603.00063/) (2026)
- [Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence](https://mlsanity.com/paper/2604.09104/) (2026)
- [Compute Requirements for Algorithmic Innovation in Frontier AI Models](https://mlsanity.com/paper/2507.10618/) (2025)
- [SOCK: A Benchmark for Measuring Self-Replication in Large Language Models](https://mlsanity.com/paper/2509.25643/) (2025)
- [Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems](https://mlsanity.com/paper/2512.23132/) (2025)
- [The Global Majority in International AI Governance](https://mlsanity.com/paper/2601.17191/) (2026)
- [The Role of AI Safety Institutes in Contributing to International Standards for Frontier AI Safety](https://mlsanity.com/paper/2409.11314/) (2024)
- [Cybersecurity threat detection based on a UEBA framework using Deep Autoencoders](https://mlsanity.com/paper/2505.11542/) (2025)
- [Highly Autonomous Cyber-Capable Agents: Anticipating Capabilities, Tactics, and Strategic Implications](https://mlsanity.com/paper/2603.11528/) (2026)

## Abstract (arXiv)

This paper applies open-source intelligence (OSINT) and cyber threat intelligence (CTI) methodologies to the problem of detecting AI systems operating outside human control. Drawing on a cross-disciplinary literature review and 14 semi-structured expert interviews conducted under Chatham House Rule, the paper develops two threat models, identifies a range of observable traces, and proposes an institutional architecture for monitoring. The research finds that OSINT-based detection of loss of control is partially feasible and worth building now. Three detection vectors emerge as highest priority: transcript-based collection of user-reported AI behaviour; infrastructure correlation for unexpected external connections or replication; and output analysis for capability concealment. The paper argues for a dedicated, federated international monitoring capability anchored in OSINT methods and independent of frontier AI developers, and identifies sustained non-industry funding as the highest-leverage structural intervention available.