4
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      DeepInception: Hypnotize Large Language Model to Be Jailbreaker

      Preprint
      , , , , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Despite remarkable success in various applications, large language models (LLMs) are vulnerable to adversarial jailbreaks that make the safety guardrails void. However, previous studies for jailbreaks usually resort to brute-force optimization or extrapolations of a high computation cost, which might not be practical or effective. In this paper, inspired by the Milgram experiment that individuals can harm another person if they are told to do so by an authoritative figure, we disclose a lightweight method, termed as DeepInception, which can easily hypnotize LLM to be a jailbreaker and unlock its misusing risks. Specifically, DeepInception leverages the personification ability of LLM to construct a novel nested scene to behave, which realizes an adaptive way to escape the usage control in a normal scenario and provides the possibility for further direct jailbreaks. Empirically, we conduct comprehensive experiments to show its efficacy. Our DeepInception can achieve competitive jailbreak success rates with previous counterparts and realize a continuous jailbreak in subsequent interactions, which reveals the critical weakness of self-losing on both open/closed-source LLMs like Falcon, Vicuna, Llama-2, and GPT-3.5/4/4V. Our investigation appeals that people should pay more attention to the safety aspects of LLMs and a stronger defense against their misuse risks. The code is publicly available at: https://github.com/tmlr-group/DeepInception.

          Related collections

          Author and article information

          Journal
          06 November 2023
          Article
          2311.03191
          c82b7025-2541-4fa7-971f-d59244fea881

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          cs.LG cs.CR

          Security & Cryptology,Artificial intelligence
          Security & Cryptology, Artificial intelligence

          Comments

          Comment on this article