English(EN) Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning

新的TTS生成后门攻击利用语音情感识别系统

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

研究人员发现了一种针对语音情感识别（SER）系统的新型后门攻击方法，该方法利用文本到语音（TTS）生成的音频。该技术将细微的声学触发器嵌入语音中，即使在低中毒率下也能以高成功率损害SER模型。研究发现，这些后门模式在不同模型之间具有可迁移性，并且自监督表示尤其容易受到攻击，这凸显了当前SER流程中存在的重大安全风险。 AI

影响这项研究突显了SER系统中的关键漏洞，可能影响依赖情感检测的AI应用的可靠性和安全性。

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: 22 / 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: 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.AI TIER_1 English(EN) · Yongbin Huang, Xihao Xie, Jia Zhang · 2026-09-03 04:00

通过TTS生成的投毒数据对语音情感识别的后门攻击

arXiv:2606.21052v2 Announce Type: replace-cross Abstract: Speech Emotion Recognition (SER) systems increasingly leverage self-supervised acoustic representations, yet their vulnerability to training-time attacks remains largely underexplored. This paper presents the first systema…

本文如何被排名

报道来源 [1]

通过TTS生成的投毒数据对语音情感识别的后门攻击

相关实体

相关话题