深度学习应用的弹性:关于分析和加固技术的系统性文献综述

IF 13.3 1区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS Computer Science Review Pub Date : 2024-10-21 DOI:10.1016/j.cosrev.2024.100682
Cristiana Bolchini, Luca Cassano, Antonio Miele
{"title":"深度学习应用的弹性:关于分析和加固技术的系统性文献综述","authors":"Cristiana Bolchini,&nbsp;Luca Cassano,&nbsp;Antonio Miele","doi":"10.1016/j.cosrev.2024.100682","DOIUrl":null,"url":null,"abstract":"<div><div>Machine Learning (ML) is currently being exploited in numerous applications, being one of the most effective Artificial Intelligence (AI) technologies used in diverse fields, such as vision, autonomous systems, and the like. The trend motivated a significant amount of contributions to the analysis and design of ML applications against faults affecting the underlying hardware. The authors investigate the existing body of knowledge on Deep Learning (among ML techniques) resilience against hardware faults systematically through a thoughtful review in which the strengths and weaknesses of this literature stream are presented clearly and then future avenues of research are set out. The review reports 85 scientific articles published between January 2019 and March 2024, after carefully analysing 222 contributions (from an initial screening of eligible 244 publications). The authors adopt a classifying framework to interpret and highlight research similarities and peculiarities, based on several parameters, starting from the main scope of the work, the adopted fault and error models, to their reproducibility. This framework allows for a comparison of the different solutions and the identification of possible synergies. Furthermore, suggestions concerning the future direction of research are proposed in the form of open challenges to be addressed.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":null,"pages":null},"PeriodicalIF":13.3000,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Resilience of deep learning applications: A systematic literature review of analysis and hardening techniques\",\"authors\":\"Cristiana Bolchini,&nbsp;Luca Cassano,&nbsp;Antonio Miele\",\"doi\":\"10.1016/j.cosrev.2024.100682\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Machine Learning (ML) is currently being exploited in numerous applications, being one of the most effective Artificial Intelligence (AI) technologies used in diverse fields, such as vision, autonomous systems, and the like. The trend motivated a significant amount of contributions to the analysis and design of ML applications against faults affecting the underlying hardware. The authors investigate the existing body of knowledge on Deep Learning (among ML techniques) resilience against hardware faults systematically through a thoughtful review in which the strengths and weaknesses of this literature stream are presented clearly and then future avenues of research are set out. The review reports 85 scientific articles published between January 2019 and March 2024, after carefully analysing 222 contributions (from an initial screening of eligible 244 publications). The authors adopt a classifying framework to interpret and highlight research similarities and peculiarities, based on several parameters, starting from the main scope of the work, the adopted fault and error models, to their reproducibility. This framework allows for a comparison of the different solutions and the identification of possible synergies. Furthermore, suggestions concerning the future direction of research are proposed in the form of open challenges to be addressed.</div></div>\",\"PeriodicalId\":48633,\"journal\":{\"name\":\"Computer Science Review\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":13.3000,\"publicationDate\":\"2024-10-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Science Review\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1574013724000662\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Science Review","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1574013724000662","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

机器学习(ML)目前正被广泛应用,是视觉、自主系统等不同领域最有效的人工智能(AI)技术之一。在这一趋势的推动下,针对影响底层硬件的故障分析和设计 ML 应用程序的工作取得了重大进展。作者通过深思熟虑的综述,系统地研究了深度学习(ML 技术中的一种)对硬件故障的适应能力的现有知识体系,清楚地介绍了这一文献流的优缺点,然后提出了未来的研究方向。在仔细分析了 222 篇投稿(从符合条件的 244 篇出版物中初步筛选)后,本综述报告了 2019 年 1 月至 2024 年 3 月间发表的 85 篇科学文章。作者采用了一个分类框架来解释和强调研究的相似性和特殊性,该框架基于多个参数,从工作的主要范围、采用的故障和误差模型到其可重复性。通过这一框架,可以对不同的解决方案进行比较,并确定可能的协同作用。此外,还以公开挑战的形式提出了有关未来研究方向的建议。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Resilience of deep learning applications: A systematic literature review of analysis and hardening techniques
Machine Learning (ML) is currently being exploited in numerous applications, being one of the most effective Artificial Intelligence (AI) technologies used in diverse fields, such as vision, autonomous systems, and the like. The trend motivated a significant amount of contributions to the analysis and design of ML applications against faults affecting the underlying hardware. The authors investigate the existing body of knowledge on Deep Learning (among ML techniques) resilience against hardware faults systematically through a thoughtful review in which the strengths and weaknesses of this literature stream are presented clearly and then future avenues of research are set out. The review reports 85 scientific articles published between January 2019 and March 2024, after carefully analysing 222 contributions (from an initial screening of eligible 244 publications). The authors adopt a classifying framework to interpret and highlight research similarities and peculiarities, based on several parameters, starting from the main scope of the work, the adopted fault and error models, to their reproducibility. This framework allows for a comparison of the different solutions and the identification of possible synergies. Furthermore, suggestions concerning the future direction of research are proposed in the form of open challenges to be addressed.
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
Computer Science Review
Computer Science Review Computer Science-General Computer Science
CiteScore
32.70
自引率
0.00%
发文量
26
审稿时长
51 days
期刊介绍: Computer Science Review, a publication dedicated to research surveys and expository overviews of open problems in computer science, targets a broad audience within the field seeking comprehensive insights into the latest developments. The journal welcomes articles from various fields as long as their content impacts the advancement of computer science. In particular, articles that review the application of well-known Computer Science methods to other areas are in scope only if these articles advance the fundamental understanding of those methods.
期刊最新文献
A systematic review on security aspects of fog computing environment: Challenges, solutions and future directions A survey of deep learning techniques for detecting and recognizing objects in complex environments Intervention scenarios and robot capabilities for support, guidance and health monitoring for the elderly Resilience of deep learning applications: A systematic literature review of analysis and hardening techniques AI-driven cluster-based routing protocols in WSNs: A survey of fuzzy heuristics, metaheuristics, and machine learning models
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1