AI deception: A survey of examples, risks, and potential solutions
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.
Record details
Published: 1 May 2024
Source: OpenAlex
Category: Research
Topics: Misinformation
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
The future of fact-checking in the algorithmic society
HKS Misinformation Review · 28 July 2026
News diary 27 July – 2 August: Apple and Meta results, Manchester mayor election and Commonwealth Games
Press Gazette (AI/journalism) · 24 July 2026
Why Would Meta Download So Much Porn?
The Atlantic Technology · 24 July 2026
Greek Finance Minister Sues Facebook Page for Deepfake Advert
AI Incident Database · 26 July 2026
Why has Nitin Gadkari sued Meta, X and Google over AI deepfakes?
MediaNama (IN) · 28 July 2026
MEA launches Instagram fact-check account after viral misinformation row
MediaNama (IN) · 30 July 2026
How to cite this record
ethics.ai (1 May 2024), “AI deception: A survey of examples, risks, and potential solutions,” evidence record 9607, https://ethics.ai/record/9607 (originally published by OpenAlex).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.