AI Deception: Risks, Dynamics, and Controls
Abstract
As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an empirically demonstrated risk across language models, AI agents, and emerging frontier systems. This project provides a comprehensive and up-to-date overview of the AI deception field, covering its core concepts, methodologies, genesis, and potential mitigations. First, we identify a formal definition of AI deception, grounded in signaling theory from studies of animal deception. We then review existing empirical studies and associated risks, highlighting deception as a sociotechnical safety challenge. We organize the landscape of AI deception research as a deception cycle, consisting of two key components: deception emergence and deception treatment. Deception emergence reveals the mechanisms underlying AI deception: systems with sufficient capability and incentive potential inevitably engage in deceptive behaviors when triggered by external conditions. Deception treatment, in turn, focuses on detecting and addressing such behaviors. On deception emergence, we analyze incentive foundations across three hierarchical levels and identify three essential capability preconditions required for deception. We further examine contextual triggers, including supervision gaps, distributional shifts, and environmental pressures. On deception treatment, we conclude detection methods covering benchmarks and evaluation protocols in static and interactive settings. Building on the three core factors of deception emergence, we outline potential mitigation strategies and propose auditing approaches that integrate technical, community, and governance efforts to address sociotechnical challenges and future AI risks. To support ongoing work in this area, we release a living resource at www.deceptionsurvey.com.
Cite
@article{arxiv.2511.22619,
title = {AI Deception: Risks, Dynamics, and Controls},
author = {Boyuan Chen and Sitong Fang and Jiaming Ji and Yanxu Zhu and Pengcheng Wen and Jinzhou Wu and Yingshui Tan and Boren Zheng and Mengying Yuan and Wenqi Chen and Donghai Hong and Alex Qiu and Xin Chen and Jiayi Zhou and Kaile Wang and Juntao Dai and Borong Zhang and Tianzhuo Yang and Saad Siddiqui and Isabella Duan and Yawen Duan and Brian Tse and Jen-Tse and Huang and Kun Wang and Baihui Zheng and Jiaheng Liu and Jian Yang and Yiming Li and Wenting Chen and Dongrui Liu and Lukas Vierling and Zhiheng Xi and Haobo Fu and Wenxuan Wang and Jitao Sang and Zhengyan Shi and Chi-Min Chan and Eugenie Shi and Simin Li and Juncheng Li and Jian Yang and Wei Ji and Dong Li and Jinglin Yang and Jun Song and Yinpeng Dong and Jie Fu and Bo Zheng and Min Yang and Yike Guo and Philip Torr and Robert Trager and Yi Zeng and Zhongyuan Wang and Yaodong Yang and Tiejun Huang and Ya-Qin Zhang and Hongjiang Zhang and Andrew Yao},
journal= {arXiv preprint arXiv:2511.22619},
year = {2025}
}