GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking

• URL: http://arxiv.org/abs/2604.09222v1
• Date: Fri, 10 Apr 2026 11:27:25 GMT
• Title: GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking
• Abstract summary: Existing audio jailbreak methods mainly optimize jailbreak success while overlooking utility preservation.<n>In practice, stronger attacks often come at the cost of degraded utility.<n>We propose a utility-aware frequency-selective jailbreak framework.
• Score: 5.912676456178024
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Audio large language models (ALLMs) enable rich speech-text interaction, but they also introduce jailbreak vulnerabilities in the audio modality. Existing audio jailbreak methods mainly optimize jailbreak success while overlooking utility preservation, as reflected in transcription quality and question answering performance. In practice, stronger attacks often come at the cost of degraded utility. To study this trade-off, we revisit existing attacks by varying their perturbation coverage in the frequency domain, from partial-band to full-band, and find that broader frequency coverage does not necessarily improve jailbreak performance, while utility consistently deteriorates. This suggests that concentrating perturbation on a subset of bands can yield a better attack-utility trade-off than indiscriminate full-band coverage. Based on this insight, we propose GRM, a utility-aware frequency-selective jailbreak framework. It ranks Mel bands by their attack contribution relative to utility sensitivity, perturbs only a selected subset of bands, and learns a reusable universal perturbation under a semantic-preservation objective. Experiments on four representative ALLMs show that GRM achieves an average Jailbreak Success Rate (JSR) of 88.46% while providing a better attack-utility trade-off than representative baselines. These results highlight the potential of frequency-selective perturbation for better balancing attack effectiveness and utility preservation in audio jailbreak. Content Warning: This paper includes harmful query examples and unsafe model responses.

Related papers

• JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization [6.473799439592539]
  JailbreakOPT is a tool-assisted framework for improving iterative single-turn jailbreak prompt optimization.<n>JailbreakOPT organizes diverse atomic jailbreak prompts into an attack tool library and composes them through a unified intra-episode optimization abstraction.<n> Experiments show that JailbreakOPT improves attack success rate (ASR) while reducing the number of attacks until success (No.A) compared with atomic single-turn attacks.
  arXiv  Detail & Related papers  (2026-06-09T20:22:29Z)
• bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs [33.470999703070866]
  Existing approaches to embedding jailbreak triggers suffer from limitations including poor generalization, compromised stealthiness, or reduced contextual usability.<n>We propose bi-GRPO, a novel RL-based framework tailored explicitly for jailbreak backdoor injection.
  arXiv  Detail & Related papers  (2025-09-24T05:56:41Z)
• Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs [61.916827858666906]
  We reveal a universal phenomenon that occurs during jailbreak attacks: Attention Slipping.<n>We show Attention Slipping is consistent across various jailbreak methods, including gradient-based token replacement, prompt-level template refinement, and in-context learning.<n>We propose Attention Sharpening, a new defense that directly counters Attention Slipping by sharpening the attention score distribution using temperature scaling.
  arXiv  Detail & Related papers  (2025-07-06T12:19:04Z)
• Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models [19.373533532464915]
  We introduce AJailBench, the first benchmark specifically designed to evaluate jailbreak vulnerabilities in LAMs.<n>We use this dataset to evaluate several state-of-the-art LAMs and reveal that none exhibit consistent robustness across attacks.<n>Our findings demonstrate that even small, semantically preserved perturbations can significantly reduce the safety performance of leading LAMs.
  arXiv  Detail & Related papers  (2025-05-21T11:47:47Z)
• AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models [19.59499038333469]
  Jailbreak attacks to large audio-language models (LALMs) are studied recently, but they achieve suboptimal effectiveness, applicability, and practicability.<n>We propose AudioJailbreak, a novel audio jailbreak attack featuring asynchrony, universality, stealthiness, and over-the-air robustness.
  arXiv  Detail & Related papers  (2025-05-20T09:10:45Z)
• 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.<n>We propose a novel black-box jailbreak method leveraging reinforcement learning (RL)<n>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)
• 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 [55.253208152184065]
  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)
• LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds [98.20826635707341]
  Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts.<n>We frame jailbreaks as inference-time misalignment and introduce LIAR, a fast, black-box, best-of-$N$ sampling attack requiring no training.<n>We also introduce a theoretical "safety net against jailbreaks" metric to quantify safety alignment strength and derive suboptimality bounds.
  arXiv  Detail & Related papers  (2024-12-06T18:02:59Z)
• h4rm3l: A language for Composable Jailbreak Attack Synthesis [48.5611060845958]
  h4rm3l is a novel approach that addresses the gap with a human-readable domain-specific language.<n>We show that h4rm3l's synthesized attacks are diverse and more successful than existing jailbreak attacks in literature.
  arXiv  Detail & Related papers  (2024-08-09T01:45:39Z)
• A StrongREJECT for Empty Jailbreaks [72.8807309802266]
  StrongREJECT is a high-quality benchmark for evaluating jailbreak performance. It scores the harmfulness of a victim model's responses to forbidden prompts. It achieves state-of-the-art agreement with human judgments of jailbreak effectiveness.
  arXiv  Detail & Related papers  (2024-02-15T18:58:09Z)

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.