Privacy and Explainability: The Effects of Data Protection on Shapley Values

Author:

Bozorgpanah Aso,Torra VicençORCID,Aliahmadipour Laya

Abstract

There is an increasing need to provide explainability for machine learning models. There are different alternatives to provide explainability, for example, local and global methods. One of the approaches is based on Shapley values. Privacy is another critical requirement when dealing with sensitive data. Data-driven machine learning models may lead to disclosure. Data privacy provides several methods for ensuring privacy. In this paper, we study how methods for explainability based on Shapley values are affected by privacy methods. We show that some degree of protection still permits to maintain the information of Shapley values for the four machine learning models studied. Experiments seem to indicate that among the four models, Shapley values of linear models are the most affected ones.

Funder

Wallenberg AI, Autonomous Systems and Software Program

Knut and Alice Wallenberg Foundation

Publisher

MDPI AG

Subject

General Medicine

Reference32 articles.

1. Hundepool, A., Domingo-Ferrer, J., Franconi, L., Giessing, S., Nordholt, E.S., Spicer, K., and de Wolf, P.-P. (2012). Statistical Disclosure Control, Wiley.

2. Torra, V. (2017). Data Privacy: Foundations, New Developments and the Big Data Challenge, Springer.

3. Abowd, J., Ashmead, R., Cumings-Menon, R., Garfinkel, S., Kifer, D., Leclerc, P., Sexton, W., Simpson, A., Task, C., and Zhuravlev, P. (2021, January 6–14). An Uncertainty Principle Is a Price of Privacy-Preserving Microdata. Proceedings of the 35th Conference on Neural Information Processing Systems, Virtual.

4. Locally differentially-private randomized response for discrete distribution learning;Pastore;J. Mach. Learn. Res.,2021

5. Reimherr, M., and Awan, J. (2019, January 8–14). Elliptical Perturbations for Differential Privacy. Proceedings of the NeurIPS 2019, Vancouver, BC, Canada.

Cited by 7 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. The Trade-off Between Privacy & Quality for Counterfactual Explanations;Proceedings of the 19th International Conference on Availability, Reliability and Security;2024-07-30

2. Explainable machine learning models with privacy;Progress in Artificial Intelligence;2024-03

3. Differential Privacy for Anomaly Detection: Analyzing the Trade-Off Between Privacy and Explainability;Communications in Computer and Information Science;2024

4. Combinations of AI Models and XAI Metrics Vulnerable to Record Reconstruction Risk;Lecture Notes in Computer Science;2024

5. Explainability of the Effects of Non-Perturbative Data Protection in Supervised Classification;2023 IEEE International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT);2023-10-26

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3