English(EN) From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion

新的攻击利用泄露的语音表示来模仿声音

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

研究人员开发了一种名为“stia”的新型攻击，该攻击仅使用简短的泄露语音表示即可模仿说话者的声音，而无需原始音频或其文字记录。该方法将语音表示转换为条件序列，并训练一个流匹配模型，以指定文本和受害者声音生成语音。实验表明，仅用3秒钟泄露的Moshi表示，该攻击就达到了很高的说话人相似度得分和很低的词错误率，凸显了当前语音交互系统中的重大隐私风险。 AI

影响凸显了语音表示方法中潜在的语音隐私风险，需要更好的安全设计。

排序理由详细介绍新攻击方法的学术论文。[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: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍新攻击方法的学术论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Ye Lu, Shen Wang, Runze Liu, Zhitao Ou, Haonan Huang, Yihan Yan, Fanghui Sun, Zhaoyang Zhang · 2026-10-27 04:00

从语音令牌到被盗声音：攻击者选择文本的说话人模仿通过表示法反演实现

arXiv:2610.34688v1 Announce Type: cross Abstract: Speech interaction systems have gradually evolved from traditional cascaded systems that use text as intermediate information to end-to-end speech language models that directly process speech representations. In some applications,…

本文如何被排名

报道来源 [1]

从语音令牌到被盗声音：攻击者选择文本的说话人模仿通过表示法反演实现

相关实体

相关话题