English(EN) Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models

新攻击揭示微调语音合成模型存在严重隐私风险

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-03 04:00

研究人员开发了一个新的黑盒成员推理攻击（MIA）框架，专门针对微调的文本到语音（TTS）模型。该框架解决了TTS系统固有的查询生成和表示工程方面的挑战。在三个最先进的TTS模型上进行的评估表明，存在显著的隐私泄露，在困难场景下，说话人级别的AUC得分高达1.0，记录级别的AUC得分在0.80到0.90之间。 AI

影响凸显了个性化语音合成中重大的隐私漏洞，可能影响用户信任和TTS开发中的数据安全实践。

排序理由该集群包含一篇详细介绍新攻击方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 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: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新攻击方法的论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Kunlin Cai, Kaiyuan Zhang, Zihang Xiang, Jinghuai Zhang, Abeer Alwan, Fnu Suya, Yuan Tian · 2026-09-03 04:00

倾听低语：针对微调TTS模型的黑盒成员推理攻击

arXiv:2609.01723v1 Announce Type: cross Abstract: Text-to-Speech (TTS) foundation models are increasingly fine-tuned on private datasets to synthesize highly personalized voices, introducing severe privacy risks by exposing both biometric identities and sensitive speech content. …

本文如何被排名

报道来源 [1]

倾听低语：针对微调TTS模型的黑盒成员推理攻击

相关实体

相关话题