隐私与可解释性的权衡:揭示不同隐私和联合学习对归因方法的影响。

IF 3 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Frontiers in Artificial Intelligence Pub Date : 2024-07-03 eCollection Date: 2024-01-01 DOI:10.3389/frai.2024.1236947
Saifullah Saifullah, Dominique Mercier, Adriano Lucieri, Andreas Dengel, Sheraz Ahmed
{"title":"隐私与可解释性的权衡:揭示不同隐私和联合学习对归因方法的影响。","authors":"Saifullah Saifullah, Dominique Mercier, Adriano Lucieri, Andreas Dengel, Sheraz Ahmed","doi":"10.3389/frai.2024.1236947","DOIUrl":null,"url":null,"abstract":"<p><p>Since the advent of deep learning (DL), the field has witnessed a continuous stream of innovations. However, the translation of these advancements into practical applications has not kept pace, particularly in safety-critical domains where artificial intelligence (AI) must meet stringent regulatory and ethical standards. This is underscored by the ongoing research in eXplainable AI (XAI) and privacy-preserving machine learning (PPML), which seek to address some limitations associated with these opaque and data-intensive models. Despite brisk research activity in both fields, little attention has been paid to their interaction. This work is the first to thoroughly investigate the effects of privacy-preserving techniques on explanations generated by common XAI methods for DL models. A detailed experimental analysis is conducted to quantify the impact of private training on the explanations provided by DL models, applied to six image datasets and five time series datasets across various domains. The analysis comprises three privacy techniques, nine XAI methods, and seven model architectures. The findings suggest non-negligible changes in explanations through the implementation of privacy measures. Apart from reporting individual effects of PPML on XAI, the paper gives clear recommendations for the choice of techniques in real applications. By unveiling the interdependencies of these pivotal technologies, this research marks an initial step toward resolving the challenges that hinder the deployment of AI in safety-critical settings.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1236947"},"PeriodicalIF":3.0000,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11253022/pdf/","citationCount":"0","resultStr":"{\"title\":\"The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods.\",\"authors\":\"Saifullah Saifullah, Dominique Mercier, Adriano Lucieri, Andreas Dengel, Sheraz Ahmed\",\"doi\":\"10.3389/frai.2024.1236947\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Since the advent of deep learning (DL), the field has witnessed a continuous stream of innovations. However, the translation of these advancements into practical applications has not kept pace, particularly in safety-critical domains where artificial intelligence (AI) must meet stringent regulatory and ethical standards. This is underscored by the ongoing research in eXplainable AI (XAI) and privacy-preserving machine learning (PPML), which seek to address some limitations associated with these opaque and data-intensive models. Despite brisk research activity in both fields, little attention has been paid to their interaction. This work is the first to thoroughly investigate the effects of privacy-preserving techniques on explanations generated by common XAI methods for DL models. A detailed experimental analysis is conducted to quantify the impact of private training on the explanations provided by DL models, applied to six image datasets and five time series datasets across various domains. The analysis comprises three privacy techniques, nine XAI methods, and seven model architectures. The findings suggest non-negligible changes in explanations through the implementation of privacy measures. Apart from reporting individual effects of PPML on XAI, the paper gives clear recommendations for the choice of techniques in real applications. By unveiling the interdependencies of these pivotal technologies, this research marks an initial step toward resolving the challenges that hinder the deployment of AI in safety-critical settings.</p>\",\"PeriodicalId\":33315,\"journal\":{\"name\":\"Frontiers in Artificial Intelligence\",\"volume\":\"7 \",\"pages\":\"1236947\"},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2024-07-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11253022/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3389/frai.2024.1236947\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/frai.2024.1236947","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

自深度学习(DL)问世以来,该领域的创新层出不穷。然而,将这些进步转化为实际应用的步伐并没有跟上,尤其是在人工智能(AI)必须满足严格的监管和道德标准的安全关键领域。目前正在进行的可解释人工智能(XAI)和隐私保护机器学习(PPML)方面的研究就凸显了这一点,这些研究试图解决与这些不透明和数据密集型模型相关的一些局限性。尽管这两个领域的研究活动都很活跃,但很少有人关注它们之间的相互作用。这项研究首次深入探讨了隐私保护技术对常见 XAI 方法生成的 DL 模型解释的影响。我们进行了详细的实验分析,以量化隐私训练对 DL 模型所提供解释的影响,并将其应用于不同领域的六个图像数据集和五个时间序列数据集。分析包括三种隐私技术、九种 XAI 方法和七种模型架构。研究结果表明,通过实施隐私措施,解释发生了不可忽略的变化。除了报告 PPML 对 XAI 的个别影响外,论文还为在实际应用中选择技术提出了明确的建议。通过揭示这些关键技术的相互依存关系,这项研究标志着朝着解决阻碍在安全关键环境中部署人工智能的挑战迈出了第一步。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods.

Since the advent of deep learning (DL), the field has witnessed a continuous stream of innovations. However, the translation of these advancements into practical applications has not kept pace, particularly in safety-critical domains where artificial intelligence (AI) must meet stringent regulatory and ethical standards. This is underscored by the ongoing research in eXplainable AI (XAI) and privacy-preserving machine learning (PPML), which seek to address some limitations associated with these opaque and data-intensive models. Despite brisk research activity in both fields, little attention has been paid to their interaction. This work is the first to thoroughly investigate the effects of privacy-preserving techniques on explanations generated by common XAI methods for DL models. A detailed experimental analysis is conducted to quantify the impact of private training on the explanations provided by DL models, applied to six image datasets and five time series datasets across various domains. The analysis comprises three privacy techniques, nine XAI methods, and seven model architectures. The findings suggest non-negligible changes in explanations through the implementation of privacy measures. Apart from reporting individual effects of PPML on XAI, the paper gives clear recommendations for the choice of techniques in real applications. By unveiling the interdependencies of these pivotal technologies, this research marks an initial step toward resolving the challenges that hinder the deployment of AI in safety-critical settings.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
6.10
自引率
2.50%
发文量
272
审稿时长
13 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信