Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis

• URL: http://arxiv.org/abs/2406.10794v3
• Date: Mon, 02 Dec 2024 21:48:47 GMT
• Title: Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis
• Authors: Yuping Lin, Pengfei He, Han Xu, Yue Xing, Makoto Yamada, Hui Liu, Jiliang Tang,
• Abstract summary: Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. This paper explores the behavior of harmful and harmless prompts in the LLM's representation space to investigate the intrinsic properties of successful jailbreak attacks.
• Score: 47.81417828399084
• License:
• Abstract: Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack strategies, there is no unified understanding on why some methods succeed and others fail. This paper explores the behavior of harmful and harmless prompts in the LLM's representation space to investigate the intrinsic properties of successful jailbreak attacks. We hypothesize that successful attacks share some similar properties: They are effective in moving the representation of the harmful prompt towards the direction to the harmless prompts. We leverage hidden representations into the objective of existing jailbreak attacks to move the attacks along the acceptance direction, and conduct experiments to validate the above hypothesis using the proposed objective. We hope this study provides new insights into understanding how LLMs understand harmfulness information.

Related papers

• Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction [32.04296423547049]
  Large Language Models (LLMs) are widely applied in various domains. We propose the Rewrite to Jailbreak (R2J) approach, a transferable black-box jailbreak method to attack LLMs.
  arXiv  Detail & Related papers  (2025-02-16T11:43:39Z)
• Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense [55.77152277982117]
  We introduce Layer-AdvPatcher, a methodology designed to defend against jailbreak attacks. We use an unlearning strategy to patch specific layers within large language models through self-augmented datasets. Our framework reduces the harmfulness and attack success rate of jailbreak attacks.
  arXiv  Detail & Related papers  (2025-01-05T19:06:03Z)
• Na'vi or Knave: Jailbreaking Language Models via Metaphorical Avatars [13.496824581458547]
  We introduce a novel attack framework that exploits the imaginative capacity of Large Language Models (LLMs) to achieve jailbreaking. Specifically, AVATAR extracts harmful entities from a given harmful target and maps them to innocuous adversarial entities. Results demonstrate that AVATAR can effectively and transferablly jailbreak LLMs and achieve a state-of-the-art attack success rate.
  arXiv  Detail & Related papers  (2024-12-10T10:14:03Z)
• Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation [71.92055093709924]
  We propose a novel method that "translates" garbled adversarial prompts into coherent and human-readable natural language adversarial prompts. It also offers a new approach to discovering effective designs for jailbreak prompts, advancing the understanding of jailbreak attacks. Our method achieves over 90% attack success rates against Llama-2-Chat models on AdvBench, despite their outstanding resistance to jailbreak attacks.
  arXiv  Detail & Related papers  (2024-10-15T06:31:04Z)
• EnJa: Ensemble Jailbreak on Large Language Models [69.13666224876408]
  Large Language Models (LLMs) are increasingly being deployed in safety-critical applications. LLMs can still be jailbroken by carefully crafted malicious prompts, producing content that violates policy regulations. We propose a novel EnJa attack to hide harmful instructions using prompt-level jailbreak, boost the attack success rate using a gradient-based attack, and connect the two types of jailbreak attacks via a template-based connector.
  arXiv  Detail & Related papers  (2024-08-07T07:46:08Z)
• Enhancing Jailbreak Attack Against Large Language Models through Silent Tokens [22.24239212756129]
  Existing jailbreaking attacks require either human experts or leveraging complicated algorithms to craft prompts. We introduce BOOST, a simple attack that leverages only the eos tokens. Our findings uncover how fragile an LLM is against jailbreak attacks, motivating the development of strong safety alignment approaches.
  arXiv  Detail & Related papers  (2024-05-31T07:41:03Z)
• LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper [16.078682415975337]
  Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) This paper proposes a lightweight yet practical defense called SELFDEFEND. It can defend against all existing jailbreak attacks with minimal delay for jailbreak prompts and negligible delay for normal user prompts.
  arXiv  Detail & Related papers  (2024-02-24T05:34:43Z)
• Coercing LLMs to do and reveal (almost) anything [80.8601180293558]
  It has been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. We argue that the spectrum of adversarial attacks on LLMs is much larger than merely jailbreaking.
  arXiv  Detail & Related papers  (2024-02-21T18:59:13Z)
• Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks [55.603893267803265]
  Large Language Models (LLMs) are susceptible to Jailbreaking attacks. Jailbreaking attacks aim to extract harmful information by subtly modifying the attack query. We focus on a new attack form, called Contextual Interaction Attack.
  arXiv  Detail & Related papers  (2024-02-14T13:45:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.