Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks

• URL: http://arxiv.org/abs/2503.00187v1
• Date: Fri, 28 Feb 2025 21:10:03 GMT
• Title: Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
• Authors: Hanjiang Hu, Alexander Robey, Changliu Liu,
• Abstract summary: Large language models (LLMs) are highly vulnerable to jailbreaking attacks.<n>We propose a safety steering framework grounded in safe control theory.<n>Our method achieves invariant safety at each turn of dialogue by learning a safety predictor.
• Score: 55.29301192316118
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models (LLMs) are highly vulnerable to jailbreaking attacks, wherein adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering unsafe inputs, they fail against multi-turn jailbreaks that exploit contextual drift over multiple interactions, gradually leading LLMs away from safe behavior. To address this challenge, we propose a safety steering framework grounded in safe control theory, ensuring invariant safety in multi-turn dialogues. Our approach models the dialogue with LLMs using state-space representations and introduces a novel neural barrier function (NBF) to detect and filter harmful queries emerging from evolving contexts proactively. Our method achieves invariant safety at each turn of dialogue by learning a safety predictor that accounts for adversarial queries, preventing potential context drift toward jailbreaks. Extensive experiments under multiple LLMs show that our NBF-based safety steering outperforms safety alignment baselines, offering stronger defenses against multi-turn jailbreaks while maintaining a better trade-off between safety and helpfulness under different multi-turn jailbreak methods. Our code is available at https://github.com/HanjiangHu/NBF-LLM .

Related papers

• Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy [31.03584769307822]
  We propose JOOD, a new Jailbreak framework via OOD-ifying inputs beyond the safety alignment. Experiments across diverse jailbreak scenarios demonstrate that JOOD effectively jailbreaks recent proprietary LLMs and MLLMs.
  arXiv  Detail & Related papers  (2025-03-26T01:25:24Z)
• Improving LLM Safety Alignment with Dual-Objective Optimization [65.41451412400609]
  Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. We propose an improved safety alignment that disentangles DPO objectives into two components: (1) robust refusal training, which encourages refusal even when partial unsafe generations are produced, and (2) targeted unlearning of harmful knowledge.
  arXiv  Detail & Related papers  (2025-03-05T18:01:05Z)
• SafeDialBench: A Fine-Grained Safety Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks [46.25325034315104]
  We propose a fine-grained benchmark SafeDialBench for evaluating the safety of Large Language Models (LLMs) Specifically, we design a two-tier hierarchical safety taxonomy that considers 6 safety dimensions and generates more than 4000 multi-turn dialogues in both Chinese and English under 22 dialogue scenarios. Notably, we construct an innovative assessment framework of LLMs, measuring capabilities in detecting, and handling unsafe information and maintaining consistency when facing jailbreak attacks.
  arXiv  Detail & Related papers  (2025-02-16T12:08:08Z)
• Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models [53.580928907886324]
  Reasoning-Augmented Conversation is a novel multi-turn jailbreak framework.<n>It reformulates harmful queries into benign reasoning tasks.<n>We show that RACE achieves state-of-the-art attack effectiveness in complex conversational scenarios.
  arXiv  Detail & Related papers  (2025-02-16T09:27:44Z)
• 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.<n>We use an unlearning strategy to patch specific layers within large language models through self-augmented datasets.<n>Our framework reduces the harmfulness and attack success rate of jailbreak attacks.
  arXiv  Detail & Related papers  (2025-01-05T19:06:03Z)
• 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.<n>We conduct a detailed analysis of seven different jailbreak methods and find that disagreements stem from insufficient observation samples.<n>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)
• Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment [97.38766396447369]
  Despite training-time safety alignment, Multimodal Large Language Models (MLLMs) remain vulnerable to jailbreak attacks. We propose Immune, an inference-time defense framework that leverages a safe reward model through controlled decoding to defend against jailbreak attacks.
  arXiv  Detail & Related papers  (2024-11-27T19:00:10Z)
• MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue [35.7801861576917]
  Large Language Models (LLMs) demonstrate outstanding performance in their reservoir of knowledge and understanding capabilities.<n>LLMs have been shown to be prone to illegal or unethical reactions when subjected to jailbreak attacks.<n>We propose a novel multi-round dialogue jailbreaking agent, emphasizing the importance of stealthiness in identifying and mitigating potential threats to human values.
  arXiv  Detail & Related papers  (2024-11-06T10:32:09Z)

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.