Lifelong Safety Alignment for Language Models

• URL: http://arxiv.org/abs/2505.20259v1
• Date: Mon, 26 May 2025 17:40:40 GMT
• Title: Lifelong Safety Alignment for Language Models
• Authors: Haoyu Wang, Zeyu Qin, Yifei Zhao, Chao Du, Min Lin, Xueqian Wang, Tianyu Pang,
• Abstract summary: We propose a lifelong safety alignment framework for jailbreaking defenses.<n>A Meta-Attacker is trained to actively discover novel jailbreaking strategies, and a Defender is trained to resist them.<n>Our framework reduces the Meta-Attacker's success rate to just 7%, enabling safer and more reliable deployment of LLMs.
• Score: 33.90238075760236
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more critical to prepare LLMs for unseen attacks that may arise during deployment. To address this, we propose a lifelong safety alignment framework that enables LLMs to continuously adapt to new and evolving jailbreaking strategies. Our framework introduces a competitive setup between two components: a Meta-Attacker, trained to actively discover novel jailbreaking strategies, and a Defender, trained to resist them. To effectively warm up the Meta-Attacker, we first leverage the GPT-4o API to extract key insights from a large collection of jailbreak-related research papers. Through iterative training, the first iteration Meta-Attacker achieves a 73% attack success rate (ASR) on RR and a 57% transfer ASR on LAT using only single-turn attacks. Meanwhile, the Defender progressively improves its robustness and ultimately reduces the Meta-Attacker's success rate to just 7%, enabling safer and more reliable deployment of LLMs in open-ended environments. The code is available at https://github.com/sail-sg/LifelongSafetyAlignment.

Related papers

• CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations [9.952498288063532]
  Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries.<n>We analyze the security protection mechanism of the LLM, and propose a framework that combines attack and defense.<n>Our method is based on the linearly separable property of LLM intermediate layer embedding, as well as the essence of jailbreak attack.
  arXiv  Detail & Related papers  (2025-07-08T14:45:21Z)
• LightDefense: A Lightweight Uncertainty-Driven Defense against Jailbreaks via Shifted Token Distribution [84.2846064139183]
  Large Language Models (LLMs) face threats from jailbreak prompts.<n>We propose LightDefense, a lightweight defense mechanism targeted at white-box models.
  arXiv  Detail & Related papers  (2025-04-02T09:21:26Z)
• 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.<n>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)
• Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities [63.603861880022954]
  We introduce ADV-LLM, an iterative self-tuning process that crafts adversarial LLMs with enhanced jailbreak ability.<n>Our framework significantly reduces the computational cost of generating adversarial suffixes while achieving nearly 100% ASR on various open-source LLMs.<n>It exhibits strong attack transferability to closed-source models, achieving 99% ASR on GPT-3.5 and 49% ASR on GPT-4, despite being optimized solely on Llama3.
  arXiv  Detail & Related papers  (2024-10-24T06:36:12Z)
• PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach [25.31933913962953]
  Large Language Models (LLMs) have gained widespread use, raising concerns about their security. We introduce PathSeeker, a novel black-box jailbreak method, which is inspired by the game of rats escaping a maze. Our method outperforms five state-of-the-art attack techniques when tested across 13 commercial and open-source LLMs.
  arXiv  Detail & Related papers  (2024-09-21T15:36:26Z)
• SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner [21.414701448926614]
  This paper introduces a generic LLM jailbreak defense framework called SelfDefend.<n>We empirically validate using mainstream GPT-3.5/4 models against major jailbreak attacks.<n>To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models.
  arXiv  Detail & Related papers  (2024-06-08T15:45:31Z)
• Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks [59.46556573924901]
  This paper introduces Defensive Prompt Patch (DPP), a novel prompt-based defense mechanism for large language models (LLMs) Unlike previous approaches, DPP is designed to achieve a minimal Attack Success Rate (ASR) while preserving the high utility of LLMs. Empirical results conducted on LLAMA-2-7B-Chat and Mistral-7B-Instruct-v0.2 models demonstrate the robustness and adaptability of DPP.
  arXiv  Detail & Related papers  (2024-05-30T14:40:35Z)
• PAL: Proxy-Guided Black-Box Attack on Large Language Models [55.57987172146731]
  Large Language Models (LLMs) have surged in popularity in recent months, but they have demonstrated capabilities to generate harmful content when manipulated. We introduce the Proxy-Guided Attack on LLMs (PAL), the first optimization-based attack on LLMs in a black-box query-only setting. Our attack achieves 84% attack success rate (ASR) on GPT-3.5-Turbo and 48% on Llama-2-7B, compared to 4% for the current state of the art.
  arXiv  Detail & Related papers  (2024-02-15T02:54:49Z)
• Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization [98.18718484152595]
  We propose to integrate goal prioritization at both training and inference stages to counteract the intrinsic conflict between the goals of being helpful and ensuring safety. Our work thus contributes to the comprehension of jailbreaking attacks and defenses, and sheds light on the relationship between LLMs' capability and safety.
  arXiv  Detail & Related papers  (2023-11-15T16:42:29Z)
• SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks [99.23352758320945]
  We propose SmoothLLM, the first algorithm designed to mitigate jailbreaking attacks on large language models (LLMs) Based on our finding that adversarially-generated prompts are brittle to character-level changes, our defense first randomly perturbs multiple copies of a given input prompt, and then aggregates the corresponding predictions to detect adversarial inputs.
  arXiv  Detail & Related papers  (2023-10-05T17:01:53Z)

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.