3
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks

      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

          Large Language Models (LLMs) are susceptible to Jailbreaking attacks, which aim to extract harmful information by subtly modifying the attack query. As defense mechanisms evolve, directly obtaining harmful information becomes increasingly challenging for Jailbreaking attacks. In this work, inspired by human practices of indirect context to elicit harmful information, we focus on a new attack form called Contextual Interaction Attack. The idea relies on the autoregressive nature of the generation process in LLMs. We contend that the prior context--the information preceding the attack query--plays a pivotal role in enabling potent Jailbreaking attacks. Specifically, we propose an approach that leverages preliminary question-answer pairs to interact with the LLM. By doing so, we guide the responses of the model toward revealing the 'desired' harmful information. We conduct experiments on four different LLMs and demonstrate the efficacy of this attack, which is black-box and can also transfer across LLMs. We believe this can lead to further developments and understanding of the context vector in LLMs.

          Related collections

          Author and article information

          Journal
          14 February 2024
          Article
          2402.09177
          537599ea-78b3-4e53-b86b-34e6f60439f0

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

          History
          Custom metadata
          29 pages
          cs.LG cs.AI cs.CL

          Theoretical computer science,Artificial intelligence
          Theoretical computer science, Artificial intelligence

          Comments

          Comment on this article