English(EN) Never Stop Speaking: a Denial-of-Service Attack on End-to-End Speech Language Models

新的拒绝服务攻击通过声学扰动目标端到端语音大语言模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-12 04:00

研究人员开发了一种专门针对端到端（E2E）语音大语言模型（LLM）的新型拒绝服务（DoS）攻击。与以往依赖文本提示操纵的攻击不同，该方法向语音输入引入了不易察觉的声学扰动。这些扰动经过优化，旨在破坏模型的自回归生成过程，导致输出延长并增加计算资源消耗，同时不会显著改变原始语音的语义内容。 AI

影响这项研究突显了新兴的端到端语音大语言模型潜在的安全漏洞，有必要开发针对声学扰动攻击的强大防御措施。

排序理由该集群包含一篇研究论文，详细介绍了一种针对特定类型AI模型的新型攻击方法。[lever_c_demoted from research: ic=1 ai=1.0]

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; 该集群包含一篇研究论文，详细介绍了一种针对特定类型AI模型的新型攻击方法。[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: 58 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。

arXiv cs.AI TIER_1 English(EN) · Shuozhe Cheng, Kunlan Xiang, Mingxuan Li, Ji Zhang, Dongxiao Liu, Wenbo Jiang · 2026-08-12 04:00

永不停止的言语：针对端到端语音语言模型的拒绝服务攻击

arXiv:2608.10405v1 Announce Type: cross Abstract: Many studies have shown that specially crafted inputs can induce large language models (LLMs) to generate excessively long outputs, resulting in significant computational overhead and resource consumption. While most existing deni…