Intention Analysis Makes LLMs A Good Jailbreak Defender

• URL: http://arxiv.org/abs/2401.06561v4
• Date: Mon, 16 Dec 2024 08:43:24 GMT
• Title: Intention Analysis Makes LLMs A Good Jailbreak Defender
• Authors: Yuqi Zhang, Liang Ding, Lefei Zhang, Dacheng Tao,
• Abstract summary: We present a simple yet highly effective defense strategy, i.e., Intention Analysis ($mathbbIA$) $mathbbIA$ works by triggering LLMs' inherent self-correct and improve ability through a two-stage process. Experiments on varying jailbreak benchmarks show that $mathbbIA$ could consistently and significantly reduce the harmfulness in responses.
• Score: 79.4014719271075
• License:
• Abstract: Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks, which limits their effectiveness in such complex scenarios. In this study, we present a simple yet highly effective defense strategy, i.e., Intention Analysis ($\mathbb{IA}$). $\mathbb{IA}$ works by triggering LLMs' inherent self-correct and improve ability through a two-stage process: 1) analyzing the essential intention of the user input, and 2) providing final policy-aligned responses based on the first round conversation. Notably, $\mathbb{IA}$ is an inference-only method, thus could enhance LLM safety without compromising their helpfulness. Extensive experiments on varying jailbreak benchmarks across a wide range of LLMs show that $\mathbb{IA}$ could consistently and significantly reduce the harmfulness in responses (averagely -48.2% attack success rate). Encouragingly, with our $\mathbb{IA}$, Vicuna-7B even outperforms GPT-3.5 regarding attack success rate. We empirically demonstrate that, to some extent, $\mathbb{IA}$ is robust to errors in generated intentions. Further analyses reveal the underlying principle of $\mathbb{IA}$: suppressing LLM's tendency to follow jailbreak prompts, thereby enhancing safety.

Related papers

• xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking [32.89084809038529]
  Black-box jailbreak is an attack where crafted prompts bypass safety mechanisms in large language models. We propose a novel black-box jailbreak method leveraging reinforcement learning (RL) We introduce a comprehensive jailbreak evaluation framework incorporating keywords, intent matching, and answer validation to provide a more rigorous and holistic assessment of jailbreak success.
  arXiv  Detail & Related papers  (2025-01-28T06:07:58Z)
• Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models [59.25318174362368]
  Jailbreaking in Large Language Models (LLMs) is a major security concern as it can deceive LLMs to generate harmful text. We conduct a detailed analysis of seven different jailbreak methods and find that disagreements stem from insufficient observation samples. We propose a novel defense called textbfActivation Boundary Defense (ABD), which adaptively constrains the activations within the safety boundary.
  arXiv  Detail & Related papers  (2024-12-22T14:18:39Z)
• LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds [98.20826635707341]
  LIAR (Leveraging Inference time Alignment to jailbReak) is a fast and efficient best-of-N approach tailored for jailbreak attacks. Our results demonstrate that a best-of-N approach is a simple yet highly effective strategy for evaluating the robustness of aligned LLMs.
  arXiv  Detail & Related papers  (2024-12-06T18:02:59Z)
• Weak-to-Strong Jailbreaking on Large Language Models [96.50953637783581]
  Large language models (LLMs) are vulnerable to jailbreak attacks. Existing jailbreaking methods are computationally costly. We propose the weak-to-strong jailbreaking attack.
  arXiv  Detail & Related papers  (2024-01-30T18:48:37Z)
• How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs [66.05593434288625]
  This paper introduces a new perspective to jailbreak large language models (LLMs) as human-like communicators. We apply a persuasion taxonomy derived from decades of social science research to generate persuasive adversarial prompts (PAP) to jailbreak LLMs. PAP consistently achieves an attack success rate of over $92%$ on Llama 2-7b Chat, GPT-3.5, and GPT-4 in $10$ trials. On the defense side, we explore various mechanisms against PAP and, found a significant gap in existing defenses.
  arXiv  Detail & Related papers  (2024-01-12T16:13:24Z)
• A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily [51.63085197162279]
  Large Language Models (LLMs) are designed to provide useful and safe responses. adversarial prompts known as 'jailbreaks' can circumvent safeguards. We propose ReNeLLM, an automatic framework that leverages LLMs themselves to generate effective jailbreak prompts.
  arXiv  Detail & Related papers  (2023-11-14T16:02:16Z)
• Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation [39.829517061574364]
  Even carefully aligned models can be manipulated maliciously, leading to unintended behaviors, known as "jailbreaks" We propose the generation exploitation attack, which disrupts model alignment by only manipulating variations of decoding methods. Our study underscores a major failure in current safety evaluation and alignment procedures for open-source LLMs.
  arXiv  Detail & Related papers  (2023-10-10T20:15:54Z)
• Safe Linear Bandits over Unknown Polytopes [39.177982674455784]
  The safe linear bandit problem (SLB) is an online approach to linear programming with unknown objective and unknown roundwise constraints. We study the tradeoffs between efficacy and smooth safety costs of SLBs over polytopes.
  arXiv  Detail & Related papers  (2022-09-27T21:13:32Z)

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.