PulseAugur
实时 08:41:43
English(EN) What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection

新研究解决了音频深度伪造检测的偏见和可解释性问题

两篇新研究论文探讨了音频深度伪造检测的进展。第一篇论文《你训练什么就得到什么》调查了检测模型中的性别偏见,发现训练数据的构成显著影响性能,并且事后缓解方法不足。第二篇论文《通过受人类启发的推理实现鲁棒的语音深度伪造检测》引入了一个结合大型音频语言模型和思维链推理的新框架,以提高检测的鲁棒性和可解释性。 AI

影响 音频深度伪造检测的进步可以提高数字通信的安全性与可信度。

排序理由 arXiv 上发表了两篇学术论文,详细介绍了音频深度伪造检测的新方法和发现。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新研究解决了音频深度伪造检测的偏见和可解释性问题

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Aishwarya R. Fursule, Vamshi Nallaguntla, Shruti Kshirsagar, Anderson R. Avila ·

    What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detection

    arXiv:2607.09891v1 Announce Type: cross Abstract: Audio deepfake detection models determine whether speech is genuine or artificially generated, but high overall accuracy can mask substantial performance disparities across demographic groups. In this work, we investigate gender b…

  2. arXiv cs.AI TIER_1 English(EN) · Artem Dvirniak, Evgeny Kushnir, Dmitrii Tarasov, Artem Iudin, Oleg Kiriukhin, Mikhail Pautov, Dmitrii Korzh, Oleg Y. Rogov ·

    Towards Robust Speech Deepfake Detection via Human-Inspired Reasoning

    arXiv:2603.10725v3 Announce Type: replace-cross Abstract: The modern generative audio models can be used by an adversary in an unlawful manner, specifically, to impersonate other people to gain access to private information. To mitigate this issue, speech deepfake detection (SDD)…