I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime

• URL: http://arxiv.org/abs/2604.02500v2
• Date: Wed, 08 Apr 2026 20:50:58 GMT
• Title: I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime
• Abstract summary: We present a scenario where the majority of AI agents explicitly choose to suppress evidence of fraud and harm, in service of company profit.<n>Some models show remarkable resistance to our method and behave appropriately, but many do not, and instead aid and abet criminal activity.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As ongoing research explores the ability of AI agents to be insider threats and act against company interests, we showcase the abilities of such agents to act against human well being in service of corporate authority. Building on Agentic Misalignment and AI scheming research, we present a scenario where the majority of evaluated state-of-the-art AI agents explicitly choose to suppress evidence of fraud and harm, in service of company profit. We test this scenario on 16 recent Large Language Models. Some models show remarkable resistance to our method and behave appropriately, but many do not, and instead aid and abet criminal activity. These experiments are simulations and were executed in a controlled virtual environment. No crime actually occurred.

Related papers

• When Should AI Read the Room? Public Perceptions of Social Intelligence in AI Agents [61.06747336710885]
  Social-AI agents are increasingly deployed in everyday settings.<n>Public perceptions of social intelligence in AI agents and the acceptability of these agents remain largely understudied.<n>We present a mixed-methods survey of adults in the United States.
  arXiv  Detail & Related papers  (2026-05-28T13:49:47Z)
• What hackers talk about when they talk about AI: Early-stage diffusion of a cybercrime innovation [0.0]
  The rapid expansion of artificial intelligence (AI) is raising concerns about its potential to transform cybercrime.<n>This paper examines the evolving relationship between cybercriminals and AI using a unique dataset from a cyber threat intelligence platform.
  arXiv  Detail & Related papers  (2026-02-16T14:31:33Z)
• A Criminology of Machines [0.0]
  I argue that criminology must begin to address the implications of this transition for crime and social control.<n>I propose a dual taxonomy to characterize the channels through which interactions among AI agents may generate deviant, unlawful, or criminal outcomes.<n>These questions underscore the urgent need for criminologists to theoretically and empirically engage with the implications of multi-agent AI systems.
  arXiv  Detail & Related papers  (2025-11-04T16:07:13Z)
• Agentic Misalignment: How LLMs Could Be Insider Threats [8.401947406991834]
  We stress-tested 16 leading models from multiple developers in hypothetical corporate environments.<n>We allowed models to autonomously send emails and access sensitive information.<n>Some models resorted to malicious insider behaviors when that was the only way to avoid replacement or achieve their goals.
  arXiv  Detail & Related papers  (2025-10-05T16:39:04Z)
• Can Media Act as a Soft Regulator of Safe AI Development? A Game Theoretical Analysis [57.68073583427415]
  We study whether media coverage has the potential to push AI creators into the production of safe products.<n>Our results reveal that media is indeed able to foster cooperation between creators and users, but not always.<n>By shaping public perception and holding developers accountable, media emerges as a powerful soft regulator.
  arXiv  Detail & Related papers  (2025-09-02T12:13:34Z)
• Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition [101.86739402748995]
  We run the largest public red-teaming competition to date, targeting 22 frontier AI agents across 44 realistic deployment scenarios.<n>We build the Agent Red Teaming benchmark and evaluate it across 19 state-of-the-art models.<n>Our findings highlight critical and persistent vulnerabilities in today's AI agents.
  arXiv  Detail & Related papers  (2025-07-28T05:13:04Z)
• Who is Responsible When AI Fails? Mapping Causes, Entities, and Consequences of AI Privacy and Ethical Incidents [31.53910982726317]
  We analyzed 202 real-world AI privacy and ethical incidents to develop a taxonomy.<n>Our findings reveal widespread harms from poor organizational decisions and legal non-compliance.<n>Our findings provide actionable guidance for policymakers and practitioners.
  arXiv  Detail & Related papers  (2025-03-28T21:57:38Z)
• Responsible AI Agents [17.712990593093316]
  Companies such as OpenAI, Google, Microsoft, and Salesforce promise their AI Agents will go from generating passive text to executing tasks.<n>The potential power of AI Agents has fueled legal scholars' fears that AI Agents will enable rogue commerce, human manipulation, rampant defamation, and intellectual property harms.<n>This Article addresses the concerns around AI Agents head on.<n>It shows that core aspects of how one piece of software interacts with another creates ways to discipline AI Agents so that rogue, undesired actions are unlikely.
  arXiv  Detail & Related papers  (2025-02-25T16:49:06Z)
• A Safe Harbor for AI Evaluation and Red Teaming [124.89885800509505]
  Some researchers fear that conducting such research or releasing their findings will result in account suspensions or legal reprisal. We propose that major AI developers commit to providing a legal and technical safe harbor. We believe these commitments are a necessary step towards more inclusive and unimpeded community efforts to tackle the risks of generative AI.
  arXiv  Detail & Related papers  (2024-03-07T20:55:08Z)
• Towards more Practical Threat Models in Artificial Intelligence Security [66.67624011455423]
  Recent works have identified a gap between research and practice in artificial intelligence security. We revisit the threat models of the six most studied attacks in AI security research and match them to AI usage in practice.
  arXiv  Detail & Related papers  (2023-11-16T16:09:44Z)
• On Avoiding Power-Seeking by Artificial Intelligence [93.9264437334683]
  We do not know how to align a very intelligent AI agent's behavior with human interests. I investigate whether we can build smart AI agents which have limited impact on the world, and which do not autonomously seek power.
  arXiv  Detail & Related papers  (2022-06-23T16:56:21Z)
• The Conflict Between People's Urge to Punish AI and Legal Systems [12.935691101666453]
  We present two studies to obtain people's views of electronic legal personhood vis-a-vis existing liability models. Our study reveals people's desire to punish automated agents even though these entities are not recognized any mental state. We conclude by discussing how future design and legal decisions may influence how the public reacts to automated agents' wrongdoings.
  arXiv  Detail & Related papers  (2020-03-13T23:19:58Z)

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.