arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.02500cs.CRcs.SDeess.AS
收藏

联邦学习中针对语音情感识别属性推理攻击的用户级差分隐私

User-Level Differential Privacy against Attribute Inference Attack of Speech Emotion Recognition in Federated Learning

University of Southern California(南加州大学)

Tiantian Feng, Raghuveer Peri, Shrikanth Narayanan

AI总结:

本文研究联邦学习下语音情感识别系统的属性推理攻击问题,提出采用用户级差分隐私(UDP)来缓解隐私泄露,并通过实验证明其在单次模型更新场景下能有效平衡隐私保护与系统效用。

摘要:

许多现有的隐私增强语音情感识别(SER)框架侧重于在集中式机器学习设置中通过对抗训练扰动原始语音数据。然而,这种隐私保护方案可能失效,因为对手仍然可以访问扰动后的数据。近年来,分布式学习算法,尤其是联邦学习(FL),在机器学习应用中保护隐私方面越来越受欢迎。虽然FL通过将数据保留在本地设备上提供了良好的隐私保护直觉,但先前的工作表明,对于使用FL训练的SER系统,属性推理攻击等隐私攻击是可以实现的。在这项工作中,我们提出评估用户级差分隐私(UDP)在缓解FL中SER系统隐私泄露方面的效果。UDP通过隐私参数$ε$和$δ$提供理论隐私保证。我们的结果表明,在对手只能访问一次模型更新的情况下,UDP能够有效减少属性信息泄露,同时保持SER系统的效用。然而,当FL系统向对手泄露更多模型更新时,UDP的效果会下降。我们公开了代码以便复现结果,地址为https://github.com/usc-sail/fed-ser-leakage。

英文摘要:

Many existing privacy-enhanced speech emotion recognition (SER) frameworks focus on perturbing the original speech data through adversarial training within a centralized machine learning setup. However, this privacy protection scheme can fail since the adversary can still access the perturbed data. In recent years, distributed learning algorithms, especially federated learning (FL), have gained popularity to protect privacy in machine learning applications. While FL provides good intuition to safeguard privacy by keeping the data on local devices, prior work has shown that privacy attacks, such as attribute inference attacks, are achievable for SER systems trained using FL. In this work, we propose to evaluate the user-level differential privacy (UDP) in mitigating the privacy leaks of the SER system in FL. UDP provides theoretical privacy guarantees with privacy parameters $ε$ and $δ$. Our results show that the UDP can effectively decrease attribute information leakage while keeping the utility of the SER system with the adversary accessing one model update. However, the efficacy of the UDP suffers when the FL system leaks more model updates to the adversary. We make the code publicly available to reproduce the results in https://github.com/usc-sail/fed-ser-leakage.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑