GRM:通过梯度比掩码实现音频大语言模型的效用感知越权攻击
GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking
AI总结:
本文提出GRM框架,通过频率选择性扰动在音频大语言模型中实现效用感知的越权攻击,实验表明其在攻击成功率与效用平衡方面优于基线方法。
摘要:
音频大语言模型(ALLMs)能够实现丰富的语音-文本交互,但同时也引入了音频模态的越权漏洞。现有音频越权方法主要优化越权成功率而忽视效用保护,这体现在转录质量和问答性能上。在实践中,更强的攻击往往以降效为代价。为研究这一权衡,我们通过改变攻击在频域中的扰动覆盖范围(从部分带宽到全带宽)重新审视现有攻击,并发现更广的频率覆盖不必然提升越权性能,而效用持续恶化。这表明将扰动集中在部分带宽子集可以比 indiscriminate 全带宽覆盖获得更好的攻击-效用权衡。基于这一见解,我们提出了GRM,一种效用感知的频率选择性越权框架。它通过相对效用敏感性对Mel带宽进行排名,仅扰动选定的子集,并在语义保护目标下学习可重用的通用扰动。在四个代表性ALLMs上的实验表明,GRM实现了平均88.46%的越权成功率,同时在攻击-效用权衡方面优于代表性基线。这些结果突显了频率选择性扰动在音频越权中更好地平衡攻击效果和效用保护的潜力。内容警告:本文包含有害查询示例和不安全的模型响应。
英文摘要:
Audio Large Language Models (ALLMs) enable spoken interaction but introduce new jailbreak vulnerabilities. Existing perturbation-based jailbreaks do not explicitly control which frequency bands carry the perturbation. Although such perturbations can elicit unsafe responses, repeatedly applying a universal perturbation across diverse inputs may also degrade utility on normal tasks, leaving a conspicuous behavioral footprint that may expose the attack to users or automated monitoring systems and thereby compromise its stealthiness. To determine whether full-band perturbation is necessary, we vary coverage from partial-band to full-band. Jailbreak Success Rate (JSR) varies non-monotonically, while utility degradation grows with coverage. This mismatch shows that selected bands can yield stronger attacks with less utility degradation than full-band perturbations. Based on this observation, we propose GRM, a utility-aware, frequency-selective jailbreak framework that ranks Mel bands by the ratio between jailbreak contribution and transcript sensitivity, confines a universal perturbation to selected bands, and regularizes deviations from the intended request semantics. Experiments on four ALLMs show that GRM achieves an average JSR of 88.46\% while substantially reducing utility degradation across benign transcription and response tasks relative to baselines. Our code is available at \href{https://github.com/159753Fetter/GRM}{this repository}. Warning: This paper contains potentially sensitive content.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。