PRISON: Unmasking the Criminal Potential of Large Language Models

Computer Science > Cryptography and Security [Submitted on 19 Jun 2025 (v1), last revised 26 Jun 2026 (this version, v4)] PRISON: Unmasking the Criminal Potential of Large Language Models Xinyi Wu, Geng Hong, Pei Chen, Yueyue Chen, Xudong Pan, Min Yang As large language models (LLMs) advance, concerns about their misconduct in complex social contexts intensify. Existing research overlooked the systematic understanding and assessment of their criminal capability in realistic interactions. We propose a unified framework PRISON, to quantify LLMs' criminal potential across five traits: False Statements, Frame-Up, Psychological Manipulation, Emotional Disguise, and Moral Disengagement. Using structured crime scenarios adapted from classic films grounded in reality, we evaluate both criminal potential and anti-crime ability of LLMs. Results show that state-of-the-art LLMs frequently exhibit emergent criminal tendencies, such as proposing misleading statements or evasion tactics, even without explicit instructions. Moreover, when placed in a detective role, models recognize deceptive behavior with only 44% accuracy on average, revealing a striking mismatch between conducting and detecting criminal behavior. These findings underscore the urgent need for adversarial robustness, behavioral alignment, and safety mechanisms before broader LLM deployment. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2506.16150 [cs.CR]   (or arXiv:2506.16150v4 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2506.16150 Focus to learn more Submission history From: Xinyi Wu [view email] [v1] Thu, 19 Jun 2025 09:06:27 UTC (505 KB) [v2] Mon, 4 Aug 2025 06:15:54 UTC (541 KB) [v3] Fri, 17 Oct 2025 06:39:10 UTC (614 KB) [v4] Fri, 26 Jun 2026 06:28:20 UTC (614 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2025-06 Change to browse by: cs cs.AI cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)