DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization

• URL: http://arxiv.org/abs/2504.18564v1
• Date: Mon, 21 Apr 2025 11:30:30 GMT
• Title: DualBreach: Efficient Dual-Jailbreaking via Target-Driven Initialization and Multi-Target Optimization
• Abstract summary: We propose DualBreach, a target-driven framework for dual-jailbreaking.<n>For black-box guardrails, DualBreach either employs a powerful open-sourced guardrail or imitates the target black-box guardrail by training a proxy model.<n>We demonstrate the effectiveness of DualBreach in dual-jailbreaking scenarios through extensive evaluation on several widely-used datasets.
• Score: 15.197413326187936
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent research has focused on exploring the vulnerabilities of Large Language Models (LLMs), aiming to elicit harmful and/or sensitive content from LLMs. However, due to the insufficient research on dual-jailbreaking -- attacks targeting both LLMs and Guardrails, the effectiveness of existing attacks is limited when attempting to bypass safety-aligned LLMs shielded by guardrails. Therefore, in this paper, we propose DualBreach, a target-driven framework for dual-jailbreaking. DualBreach employs a Target-driven Initialization (TDI) strategy to dynamically construct initial prompts, combined with a Multi-Target Optimization (MTO) method that utilizes approximate gradients to jointly adapt the prompts across guardrails and LLMs, which can simultaneously save the number of queries and achieve a high dual-jailbreaking success rate. For black-box guardrails, DualBreach either employs a powerful open-sourced guardrail or imitates the target black-box guardrail by training a proxy model, to incorporate guardrails into the MTO process. We demonstrate the effectiveness of DualBreach in dual-jailbreaking scenarios through extensive evaluation on several widely-used datasets. Experimental results indicate that DualBreach outperforms state-of-the-art methods with fewer queries, achieving significantly higher success rates across all settings. More specifically, DualBreach achieves an average dual-jailbreaking success rate of 93.67% against GPT-4 with Llama-Guard-3 protection, whereas the best success rate achieved by other methods is 88.33%. Moreover, DualBreach only uses an average of 1.77 queries per successful dual-jailbreak, outperforming other state-of-the-art methods. For the purpose of defense, we propose an XGBoost-based ensemble defensive mechanism named EGuard, which integrates the strengths of multiple guardrails, demonstrating superior performance compared with Llama-Guard-3.

Related papers

• RL-MTJail: Reinforcement Learning for Automated Black-Box Multi-Turn Jailbreaking of Large Language Models [60.201244463046784]
  Large language models are vulnerable to jailbreak attacks.<n>This paper studies black-box multi-turn jailbreaks, aiming to train attacker LLMs to elicit harmful content from black-box models.
  arXiv  Detail & Related papers  (2025-12-08T17:42:59Z)
• Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models [54.61181161508336]
  We introduce Multi-Faceted Attack (MFA), a framework that exposes general safety vulnerabilities in leading defense-equipped Vision-Language Models (VLMs)<n>The core component of MFA is the Attention-Transfer Attack (ATA), which hides harmful instructions inside a meta task with competing objectives.<n>MFA achieves a 58.5% success rate and consistently outperforms existing methods.
  arXiv  Detail & Related papers  (2025-11-20T07:12:54Z)
• Black-Box Guardrail Reverse-engineering Attack [12.937652779951156]
  We present the first study of black-box LLM guardrail reverse-engineering attacks.<n>We propose Guardrail Reverse-engineering Attack (GRA), a reinforcement learning-based framework.<n>GRA achieves a rule matching rate exceeding 0.92 while requiring less than $85 in API costs.
  arXiv  Detail & Related papers  (2025-11-06T09:24:49Z)
• Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks [18.3415330691504]
  "jailbreak" attacks exploit adversarial prompts to bypass safety alignment mechanisms.<n>We propose the Bi Intention Inference Defense (BIID) to address this challenge.<n>BIID integrates forward request-based intention inference with backward response-based intention retrospection.
  arXiv  Detail & Related papers  (2025-09-25T13:29:48Z)
• Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses [4.706534644850809]
  Two primary inference-phase threats are token-level and prompt-level jailbreaks.<n>We propose two hybrid approaches that integrate token- and prompt-level techniques to enhance jailbreak effectiveness across diverse PTLMs.
  arXiv  Detail & Related papers  (2025-06-27T07:26:33Z)
• Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation [18.37303422539757]
  We investigate the vulnerability of intent-aware guardrails and demonstrate that large language models exhibit implicit intent detection capabilities.<n>We propose a two-stage intent-based prompt-refinement framework, IntentPrompt, that first transforms harmful inquiries into structured outlines and further reframes them into declarative-style narratives.<n>Our framework consistently outperforms several cutting-edge jailbreak methods and evades even advanced Intent Analysis (IA) and Chain-of-Thought (CoT)-based defenses.
  arXiv  Detail & Related papers  (2025-05-24T06:47:32Z)
• T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks [67.91652526657599]
  We formalize the T2V jailbreak attack as a discrete optimization problem and propose a joint objective-based optimization framework, called T2V-OptJail.<n>We conduct large-scale experiments on several T2V models, covering both open-source models and real commercial closed-source models.<n>The proposed method improves 11.4% and 10.0% over the existing state-of-the-art method in terms of attack success rate.
  arXiv  Detail & Related papers  (2025-05-10T16:04:52Z)
• 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.<n>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)
• Adversarial Training for Multimodal Large Language Models against Jailbreak Attacks [17.75247947379804]
  We present the first adversarial training paradigm tailored to defend against jailbreak attacks during the MLLM training phase.<n>We introduce Projection Layer Against Adversarial Training (ProEAT), an end-to-end AT framework.<n>ProEAT achieves state-of-the-art defense performance, outperforming existing baselines by an average margin of +34% across text and image modalities.
  arXiv  Detail & Related papers  (2025-03-05T14:13:35Z)
• Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees [3.6787328174619254]
  Two-stage Learning-to-Defer (L2D) enables optimal task delegation by assigning each input to either a fixed main model or one of several offline experts.<n>Existing L2D frameworks assume clean inputs and are vulnerable to adversarial perturbations that can manipulate query allocation.<n>We present the first comprehensive study of adversarial robustness in two-stage L2D systems.
  arXiv  Detail & Related papers  (2025-02-03T03:44:35Z)
• The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense [56.32083100401117]
  The vulnerability of Vision Large Language Models (VLLMs) to jailbreak attacks appears as no surprise.<n>Recent defense mechanisms against these attacks have reached near-saturation performance on benchmark evaluations.
  arXiv  Detail & Related papers  (2024-11-13T07:57:19Z)
• 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)
• Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs [13.317364896194903]
  We propose a two-stage adversarial tuning framework to enhance Large Language Models' generalized defense capabilities. In the first stage, we introduce the hierarchical meta-universal adversarial prompt learning to efficiently generate token-level adversarial prompts. In the second stage, we propose the automatic adversarial prompt learning to iteratively refine semantic-level adversarial prompts.
  arXiv  Detail & Related papers  (2024-06-07T15:37:15Z)
• Improved Generation of Adversarial Examples Against Safety-aligned LLMs [72.38072942860309]
  Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. In this paper, we explore a new perspective on this problem, suggesting that it can be alleviated by leveraging innovations inspired in transfer-based attacks. We show that 87% of the query-specific adversarial suffixes generated by the developed combination can induce Llama-2-7B-Chat to produce the output that exactly matches the target string on AdvBench.
  arXiv  Detail & Related papers  (2024-05-28T06:10:12Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• Fight Back Against Jailbreaking via Prompt Adversarial Tuning [23.55544992740663]
  Large Language Models (LLMs) are susceptible to jailbreaking attacks. We propose an approach named Prompt Adversarial Tuning (PAT) that trains a prompt control attached to the user prompt as a guard prefix. Our method is effective against both grey-box and black-box attacks, reducing the success rate of advanced attacks to nearly 0%.
  arXiv  Detail & Related papers  (2024-02-09T09:09:39Z)

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.