AI deception: A survey of examples, risks, and potential solutions

AI deception: A survey of examples, risks, and potential solutions

Peter S. Park,1,4,* Simon Goldstein,2,3,4 Aidan O’Gara,3 Michael Chen,3 and Dan Hendrycks3 1Department of Physics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA 2Dianoia Institute of Philosophy, Australian Catholic University, East Melbourne, VIC 3002, Australia 3Center for AI Safety, San Francisco, CA 94111, USA 4These authors contributed equally *Correspondence: [email protected]

https://doi.org/10.1016/j.patter.2024.100988

chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://www.cell.com/action/showPdf

“OPEN ACCESS THE BIGGER PICTURE

AI systems are already capable of deceiving humans. Deception is the systematic inducement of false beliefs in others to accomplish some outcome other than the truth. Large language models and other AI systems have already learned, from their training, the ability to deceive via techniques such as manipulation, sycophancy, and cheating the safety test. AI’s increasing capabilities at deception pose serious risks, ranging from short-term risks, such as fraud and election tampering, to long-term risks, such as losing control of AI systems. Proactive solutions are needed, such as regulatory frameworks to assess AI deception risks, laws requiring transparency about AI interactions, and further research into detecting and preventing AI deception. Proactively addressing the problem of AI deception is crucial to ensure that AI acts as a beneficial technology that augments rather than destabilizes human knowledge, discourse, and institutions.

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. Finally, we outline several potential solutions: first, regulatory frameworks should subject AI systems that are capable of deception to robust risk-assessment requirements; second, policymakers should implement bot-or-not laws; and finally, policymakers should prioritize the funding of relevant research, including tools to detect AI deception and to make AI systems less deceptive. Policymakers, researchers, and the broader public should work proactively to prevent AI deception from destabilizing the shared foundations of our society.”