mlsanityData to 14 Oct 2026

I'm Sorry Dave: How the old world of personnel security can inform the new world of AI insider risk

arXiv 2504.00012 ↗First posted 26 Mar 2025cs.CR cs.CY cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Organisations are rapidly adopting artificial intelligence (AI) tools to perform tasks previously undertaken by people. The potential benefits are enormous. Separately, some organisations deploy personnel security measures to mitigate the security risks arising from trusted human insiders. Unfortunately, there is no meaningful interplay between the rapidly evolving domain of AI and the traditional world of personnel security. This is a problem. The complex risks from human insiders are hard enough to understand and manage, despite many decades of effort. The emerging security risks from AI insiders are even more opaque. Both sides need all the help they can get. Some of the concepts and approaches that have proved useful in dealing with human insiders are also applicable to the emerging risks from AI insiders.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 60 references that are in the map. First posted on arXiv 26 Mar 2025.

Builds on

25 of 60 references.

References · 25

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2024A Survey on LLM-as-a-Judgecited by 1,423
  3. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  4. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
  5. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 529
  6. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  7. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 422
  8. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 401
  9. 2023How is ChatGPT's behavior changing over time?cited by 270
  10. 2023AI Deception: A Survey of Examples, Risks, and Potential Solutionscited by 188
  11. 2023Large Language Models can Strategically Deceive their Users when Put Under Pressurecited by 146
  12. 2023Deception Abilities Emerged in Large Language Modelscited by 101
13 more
  1. 2024Sycophancy in Large Language Models: Causes and Mitigationscited by 101
  2. 2024MoralBench: Moral Evaluation of LLMscited by 50
  3. 2025Fully Autonomous AI Agents Should Not be Developedcited by 45
  4. 2023Self-Assessment Tests are Unreliable Measures of LLM Personalitycited by 39
  5. 2023How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilitiescited by 33
  6. 2024Do LLMs "know" internally when they follow instructions?cited by 26
  7. 2024Do LLMs estimate uncertainty well in instruction-following?cited by 26
  8. 2024BeHonest: Benchmarking Honesty in Large Language Modelscited by 24
  9. 2024Evaluating Large Language Models with Psychometricscited by 22
  10. 2024Establishing and Evaluating Trustworthy AI: Overview and Research Challengescited by 12
  11. 2024Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systemscited by 3
  12. 2024Generative AI in Cybersecuritycited by 2
  13. 2024View From Above: A Framework for Evaluating Distribution Shifts in Model Behaviorcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Red Teaming AI Red Teamingcited by 3