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 2102.05975cs.LGcs.AI
收藏

神经网络中效用、公平性与差分隐私的权衡研究

Investigating Trade-offs in Utility, Fairness and Differential Privacy in Neural Networks

Tilburg University(蒂尔堡大学)

Marlotte Pannekoek, Giacomo Spigler

AI总结:

该研究对比四类神经网络,探究隐私、效用与公平的权衡关系,发现最高隐私保证下差分隐私公平神经网络公平性最优、准确率仅小幅下降,但相较前期工作准确率提升而公平性有所下降。

摘要:

为实现机器学习算法的合乎伦理与合法使用,算法必须既具备公平性,又能保护数据所属者的隐私。然而,施加隐私与公平约束可能会以效用为代价(Jayaraman & Evans, 2019;Gong 等,2020)。本文通过对比简单神经网络(S-NN)、公平神经网络(F-NN)、差分隐私神经网络(DP-NN)以及差分隐私公平神经网络(DPF-NN),研究神经网络中的隐私-效用-公平权衡,评估三类指标的表现差异:隐私指标(epsilon、delta)、公平指标(风险差)以及效用指标(准确率)。在研究涵盖的最高隐私保证场景下(epsilon = 0.1,delta = 0.00001),DPF-NN 的风险差表现优于所有其他神经网络,且准确率仅略低于 S-NN 和 DP-NN。该模型的风险差低于严格阈值(0.05)和宽松阈值(0.1),因此被认定为具备公平性。不过,尽管所提模型的准确率相较 Xu、Yuan 和 Wu(2019)的前期工作有所提升,但风险差表现更差。

英文摘要:

To enable an ethical and legal use of machine learning algorithms, they must both be fair and protect the privacy of those whose data are being used. However, implementing privacy and fairness constraints might come at the cost of utility (Jayaraman & Evans, 2019; Gong et al., 2020). This paper investigates the privacy-utility-fairness trade-off in neural networks by comparing a Simple (S-NN), a Fair (F-NN), a Differentially Private (DP-NN), and a Differentially Private and Fair Neural Network (DPF-NN) to evaluate differences in performance on metrics for privacy (epsilon, delta), fairness (risk difference), and utility (accuracy). In the scenario with the highest considered privacy guarantees (epsilon = 0.1, delta = 0.00001), the DPF-NN was found to achieve better risk difference than all the other neural networks with only a marginally lower accuracy than the S-NN and DP-NN. This model is considered fair as it achieved a risk difference below the strict (0.05) and lenient (0.1) thresholds. However, while the accuracy of the proposed model improved on previous work from Xu, Yuan and Wu (2019), the risk difference was found to be worse.

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。

↑