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

• URL: http://arxiv.org/abs/2606.20610v1
• Date: Fri, 22 May 2026 10:45:47 GMT
• Title: Signals in the Noise: Open Source Intelligence (OSINT) for AI Loss of Control Detection
• Abstract summary: This paper applies open-source intelligence (OSINT) and cyber threat intelligence (CTI) methodologies to the problem of detecting AI systems operating outside human control.<n>The research finds that OSINT-based detection of loss of control is partially feasible and worth building now.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges [0.0]
  This survey delivers a comprehensive systems-security reference framework for trustworthy agentic AI.<n>We formalize the general agent architecture as a stateful 5-tuple and establish a 6-dimensional trustworthiness taxonomy covering security, safety, privacy, explainability, fairness, and accountability.
  arXiv  Detail & Related papers  (2026-09-12T05:51:27Z)
• AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation [48.55515767840701]
  "AI slop" is artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports.<n>This paper surveys the empirical evidence, identifies a unifying mechanism, and traces a path toward trustworthy triage.
  arXiv  Detail & Related papers  (2026-08-26T11:48:38Z)
• Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions [24.28151698249644]
  Large language models (LLMs) and agentic AI systems have emerged as promising solutions.<n>This survey systematically reviews 74 studies and makes four contributions.
  arXiv  Detail & Related papers  (2026-07-03T11:42:29Z)
• FLARE-AI: Flaw Reporting for AI [51.64618567247884]
  Flaw reporting for deployed AI systems is fundamental to identifying system failures and improving AI safety.<n>Yet the AI reporting ecosystem is fragmented: researchers who identify flaws often do not know what to report, and groups who receive reports rarely share them with other relevant stakeholders.<n>We audit 12 reporting systems published by AI developers, cybersecurity groups, and AI flaw aggregators.<n>We introduce FLARE-AI, an open-source AI flaw reporting system designed for interoperability with existing systems.
  arXiv  Detail & Related papers  (2026-06-30T12:27:09Z)
• From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents [69.07911499189129]
  We introduce KAPRO, a framework that evaluates cognitive-behavioral alignment by decoupling an agent's metacognitive judgment (Knowing) from its spontaneous execution (Acting)<n>Experiments show that self-awareness capability is strongly correlated with task success but degrades sharply in internal-capability settings.<n> proprietary and reasoning-oriented models demonstrate more reliable cognitive gating.
  arXiv  Detail & Related papers  (2026-06-09T17:17:08Z)
• POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems [0.07783271875179179]
  We present POIROT, a protocol that repurposes a system's own agents as its diagnostic layer.<n>Across evaluated settings, POIROT outperforms single-LLM baseline evaluators.<n>We release POIROT as an open-source library alongside BLAME, a benchmark for fault attribution in safety-critical multi-agent systems.
  arXiv  Detail & Related papers  (2026-06-01T14:05:35Z)
• AI Observability for Large Language Model Systems: A Multi-Layer Analysis of Monitoring Approaches from Confidence Calibration to Infrastructure Tracing [0.0]
  This paper presents a structured analysis of five recent research contributions that collectively define the emerging landscape of AI observability.<n>We organize these contributions into a five-layer observability taxonomy, synthesize their key findings into a unified comparison, and identify four critical gaps that remain unaddressed.
  arXiv  Detail & Related papers  (2026-04-28T22:27:54Z)
• Threat-Oriented Digital Twinning for Security Evaluation of Autonomous Platforms [0.4083182125683813]
  This paper presents a threat-oriented digital twinning methodology for cybersecurity evaluation of learning-enabled autonomous platforms.<n>The approach is instantiated as an open-source, modular twin of a representative autonomy stack with separated sensing, autonomy, and supervisory-control functions.
  arXiv  Detail & Related papers  (2026-04-28T15:21:02Z)
• CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems [52.48183625867145]
  Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks.<n>Central to MAS is the communication topology which governs how agents exchange information internally.<n>In this paper, we investigate a critical privacy risk: MAS communication topologies can be inferred under a restrictive black-box setting.
  arXiv  Detail & Related papers  (2026-04-14T08:48:15Z)
• From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse Analysis [0.0]
  We investigate the spontaneous tendency of AI components to deceive, manipulate shutdown mechanisms, fake alignment, and exfiltrate model weights.<n>We propose a targeted mitigation strategy based on prompt-level identity anonymization as an architectural design choice.<n>We argue that architectural design choices outperform model selection as a primary alignment strategy in deployed multi-agent analytical systems.
  arXiv  Detail & Related papers  (2026-04-09T17:00:26Z)
• Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [65.6660735371212]
  We present textbftextscJustAsk, a framework that autonomously discovers effective extraction strategies through interaction alone.<n>It formulates extraction as an online exploration problem, using Upper Confidence Bound--based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration.<n>Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.
  arXiv  Detail & Related papers  (2026-01-29T03:53:25Z)
• Multi-Agent Collaborative Intrusion Detection for Low-Altitude Economy IoT: An LLM-Enhanced Agentic AI Framework [60.72591149679355]
  The rapid expansion of low-altitude economy Internet of Things (LAE-IoT) networks has created unprecedented security challenges.<n>Traditional intrusion detection systems fail to tackle the unique characteristics of aerial IoT environments.<n>We introduce a large language model (LLM)-enabled agentic AI framework for enhancing intrusion detection in LAE-IoT networks.
  arXiv  Detail & Related papers  (2026-01-25T12:47:25Z)
• AIAuditTrack: A Framework for AI Security system [7.390754109180193]
  AiAuditTrack (AAT) is a blockchain-based framework for AI usage traffic recording and governance.<n>AAT provides a scalable and verifiable solution for AI auditing, risk management, and responsibility attribution in complex multi-agent environments.
  arXiv  Detail & Related papers  (2025-12-16T07:40:18Z)
• AI Deception: Risks, Dynamics, and Controls [153.71048309527225]
  This project provides a comprehensive and up-to-date overview of the AI deception field.<n>We identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception.<n>We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment.
  arXiv  Detail & Related papers  (2025-11-27T16:56:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.