Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses

• URL: http://arxiv.org/abs/2506.21972v1
• Date: Fri, 27 Jun 2025 07:26:33 GMT
• Title: Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses
• Authors: Mohamed Ahmed, Mohamed Abdelmouty, Mingyu Kim, Gunvanth Kandula, Alex Park, James C. Davis,
• Abstract summary: 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.
• Score: 4.706534644850809
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The advancement of Pre-Trained Language Models (PTLMs) and Large Language Models (LLMs) has led to their widespread adoption across diverse applications. Despite their success, these models remain vulnerable to attacks that exploit their inherent weaknesses to bypass safety measures. Two primary inference-phase threats are token-level and prompt-level jailbreaks. Token-level attacks embed adversarial sequences that transfer well to black-box models like GPT but leave detectable patterns and rely on gradient-based token optimization, whereas prompt-level attacks use semantically structured inputs to elicit harmful responses yet depend on iterative feedback that can be unreliable. To address the complementary limitations of these methods, we propose two hybrid approaches that integrate token- and prompt-level techniques to enhance jailbreak effectiveness across diverse PTLMs. GCG + PAIR and the newly explored GCG + WordGame hybrids were evaluated across multiple Vicuna and Llama models. GCG + PAIR consistently raised attack-success rates over its constituent techniques on undefended models; for instance, on Llama-3, its Attack Success Rate (ASR) reached 91.6%, a substantial increase from PAIR's 58.4% baseline. Meanwhile, GCG + WordGame matched the raw performance of WordGame maintaining a high ASR of over 80% even under stricter evaluators like Mistral-Sorry-Bench. Crucially, both hybrids retained transferability and reliably pierced advanced defenses such as Gradient Cuff and JBShield, which fully blocked single-mode attacks. These findings expose previously unreported vulnerabilities in current safety stacks, highlight trade-offs between raw success and defensive robustness, and underscore the need for holistic safeguards against adaptive adversaries.

Related papers

• Wolf Hidden in Sheep's Conversations: Toward Harmless Data-Based Backdoor Attacks for Jailbreaking Large Language Models [69.11679786018206]
  Supervised fine-tuning (SFT) aligns large language models with human intent by training them on labeled task-specific data.<n>Recent studies have shown that malicious attackers can inject backdoors into these models by embedding triggers into the harmful question-answer pairs.<n>We propose a novel clean-data backdoor attack for jailbreaking LLMs.
  arXiv  Detail & Related papers  (2025-05-23T08:13:59Z)
• Alignment Under Pressure: The Case for Informed Adversaries When Evaluating LLM Defenses [6.736255552371404]
  Alignment is one of the main approaches used to defend against attacks such as prompt injection and jailbreaks.<n>Recent defenses report near-zero Attack Success Rates (ASR) even against Greedy Coordinate Gradient (GCG)
  arXiv  Detail & Related papers  (2025-05-21T16:43:17Z)
• 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)
• 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)
• Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation [12.303965802578087]
  This paper introduces the GAP (Graph of Attacks with Pruning) framework for generating stealthy jailbreak prompts.<n>GAP addresses limitations in existing tree-based LLM jailbreak methods by implementing an interconnected graph structure.<n>We present specialized variants like GAP-Auto for automated seed generation and GAP-VLM for multimodal attacks.
  arXiv  Detail & Related papers  (2025-01-28T17:10:20Z)
• Boosting Jailbreak Transferability for Large Language Models [10.884050438726215]
  We propose a scenario induction template, optimized suffix selection, and the integration of re-suffix attack mechanism to reduce inconsistent outputs. Our approach has shown superior performance in extensive experiments across various benchmarks, achieving nearly 100% success rates in both attack execution and transferability.
  arXiv  Detail & Related papers  (2024-10-21T05:11:19Z)
• 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)<n>Unlike previous approaches, DPP is designed to achieve a minimal Attack Success Rate (ASR) while preserving the high utility of LLMs.<n> 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)
• 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)
• Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing [107.97160023681184]
  Aligned large language models (LLMs) are vulnerable to jailbreaking attacks. We propose SEMANTICSMOOTH, a smoothing-based defense that aggregates predictions of semantically transformed copies of a given input prompt.
  arXiv  Detail & Related papers  (2024-02-25T20:36:03Z)

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.