{
  "id": 9607,
  "url": "https://doi.org/10.1016/j.patter.2024.100988",
  "title": "AI deception: A survey of examples, risks, and potential solutions",
  "summary": "This paper argues that a range of current AI systems have learned how to deceive humans. We define deception as the systematic inducement of false beliefs in the pursuit of some outcome other than the truth. We first survey empirical examples of AI deception, discussing both special-use AI systems (including Meta's CICERO) and general-purpose AI systems (including large language models). Next, we detail several risks from AI deception, such as fraud, election tampering, and losing control of AI.",
  "authors": "Peter S. Park, Simon Goldstein, Aidan O’Gara, Michael Chen, Dan Hendrycks",
  "category": "research",
  "topics": "misinformation",
  "orgs": "meta",
  "regions": null,
  "published_at": "2024-05-01T00:00:00.000Z",
  "fetched_at": "2026-07-14T16:33:57.580Z",
  "source_slug": "openalex",
  "source_name": "OpenAlex",
  "source_homepage": "https://openalex.org",
  "ethics_ai_record_url": "https://ethics.ai/record/9607",
  "original_url": "https://doi.org/10.1016/j.patter.2024.100988",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}