新型攻击通过潜在空间操纵绕过音频LLM防御

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-22 04:00

研究人员开发了一种名为CodecAttack的新型对抗性攻击，该攻击可以绕过音频大型语言模型（LLM）中的压缩防御。与先前直接扰动音频波形的方法不同，CodecAttack在神经音频编解码器的潜在空间中优化扰动。该技术被证明非常有效，在Opus压缩上实现了平均85.5%的攻击成功率，并证明了其对MP3和AAC-LC等其他编解码器的可迁移性。 AI

影响证明有损压缩并非对抗性音频的可靠防御手段，对已部署的音频LLM系统构成实际威胁。

排序理由详细介绍攻击AI模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍攻击AI模型新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 100 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Jaechul Roh, Jean-Philippe Monteuuis, Jonathan Petit, Amir Houmansdar · 2026-05-22 04:00

Codec-Robust Attacks on Audio LLMs

arXiv:2605.20519v1 Announce Type: cross Abstract: Prior attacks on Audio Large Language Models (Audio LLMs) demonstrated that carefully crafted waveform-domain perturbations can force targeted adversarial outputs. As a defense mechanism against these attacks, real-world codec com…

本文如何被排名

报道来源 [1]

Codec-Robust Attacks on Audio LLMs

相关实体

相关话题