提出新方法保护语音情绪识别中的说话人属性隐私，兼顾安全与性能。
Investigating Effective Speaker Property Privacy Protection in Federated Learning for Speech Emotion Recognition
- 分解语音属性并添加扰动，增强联邦学习中的隐私保护
- 在保持模型性能的同时，显著提升对属性推断攻击的防御能力
- 适用于语音处理领域的隐私保护研究，尤其关注安全与效用平衡
联邦学习（FL）是一种隐私保护方法，通过聚合本地客户端传输的分布式模型来训练，而非直接使用用户数据。近年来，该技术被应用于语音情绪识别（SER），以实现安全的人机交互。然而，最新研究发现，联邦学习仍面临推理攻击的风险。为此，本文聚焦于评估联邦学习在语音情绪识别中针对属性推理攻击的安全性，提出一种新方法：通过分解语音中的多种属性并对其添加扰动，以保护语音数据中的属性信息。实验表明，所提方法在隐私-效用权衡上优于现有方法，在有效防范攻击的同时，维持了相近的联邦学习性能水平。本工作可为语音处理领域未来的隐私保护方法设计提供指导。
原文摘要 · Abstract (English)
Federated Learning (FL) is a privacy-preserving approach that allows servers to aggregate distributed models transmitted from local clients rather than training on user data. More recently, FL has been applied to Speech Emotion Recognition (SER) for secure human-computer interaction applications. Recent research has found that FL is still vulnerable to inference attacks. To this end, this paper focuses on investigating the security of FL for SER concerning property inference attacks. We propose a novel method to protect the property information in speech data by decomposing various properties in the sound and adding perturbations to these properties. Our experiments show that the proposed method offers better privacy-utility trade-offs than existing methods. The trade-offs enable more effective attack prevention while maintaining similar FL utility levels. This work can guide future work on privacy protection methods in speech processing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。