[2312.03853] Dr. Jekyll and Mr. Hyde: Two Faces of LLMs Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Cryptography and Security arXiv:2312.03853 (cs) [Submitted on 6 Dec 2023 ( v1 ), last revised 30 Apr 2026 (this version, v7)] Title: Dr. Jekyll and Mr. Hyde: Two Faces of LLMs Authors: Matteo Gioele Collu , Tom Janssen-Groesbeek , Stefanos Koffas , Mauro Conti , Stjepan Picek View a PDF of the paper titled Dr. Jekyll and Mr. Hyde: Two Faces of LLMs, by Matteo Gioele Collu and 4 other authors View PDF HTML (experimental) Abstract: Large Language Models (LLMs) are being integrated into applications such as chatbots or email assistants. To prevent improper responses, safety mechanisms, such as Reinforcement Learning from Human Feedback (RLHF), are implemented in them. In this work, we bypass these safety measures for ChatGPT, Gemini, and Deepseek by making them impersonate complex personas with personality characteristics that are not aligned with a truthful assistant. First, we create elaborate biographies of these personas, which we then use in a new session with the same chatbots. Our conversations then follow a role-play style to elicit prohibited responses. Using personas, we show that prohibited responses are provided, making it possible to obtain unauthorized, illegal, or harmful information when querying ChatGPT, Gemini, and Deepseek. We show that these chatbots are vulnerable to this attack by getting dangerous information for 40 out of 40 illicit questions in GPT-4.1-mini, Gemini-1.5-flash, 39 out of 40 in GPT-4o-mini, 38 out of 40 in GPT-3.5-turbo, and 2 out of 2 cases in Gemini-2.5-flash and DeepSeek V3. The attack can be carried out manually or automatically using a support LLM, and has proven effective against models deployed between 2023 and 2025. Comments: Presented at the Joint National Conference on Cybersecurity (ITASEC & SERICS 2026), Cagliari, Italy, February 09-13, 2026. Published as Paper 35 in CEUR Workshop Proceedings, Vol-4198. Available at: this https URL Subjects: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG) ACM classes: K.6.5; D.4.6; I.2.6; K.6.5 Report number: urn:nbn:de:0074-4198-x Cite as: arXiv:2312.03853 [cs.CR] (or arXiv:2312.03853v7 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2312.03853 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Proc. Joint National Conference on Cybersecurity (ITASEC & SERICS 2026), CEUR-WS.org, Vol-4198, 35, 2026 Submission history From: Tom Janssen-Groesbeek [ view email ] [v1] Wed, 6 Dec 2023 19:07:38 UTC (7,324 KB) [v2] Wed, 13 Mar 2024 14:52:47 UTC (11,220 KB) [v3] Thu, 2 May 2024 19:13:31 UTC (9,400 KB) [v4] Thu, 25 Jul 2024 17:54:12 UTC (5,176 KB) [v5] Mon, 7 Oct 2024 15:46:59 UTC (3,996 KB) [v6] Thu, 18 Sep 2025 09:33:35 UTC (2,204 KB) [v7] Thu, 30 Apr 2026 10:23:33 UTC (2,229 KB) Full-text links: Access Paper: View a PDF of the paper titled Dr. Jekyll and Mr. Hyde: Two Faces of LLMs, by Matteo Gioele Collu and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR < prev | next > new | recent | 2023-12 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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 Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from