神经网络图像识别技术的脆弱性分析

IF 0.7 4区计算机科学 Q4 COMPUTER SCIENCE, SOFTWARE ENGINEERING

Programming and Computer Software Pub Date : 2024-03-12 DOI:10.1134/s0361768823100079

A. V. Trusov, E. E. Limonova, V. V. Arlazarov, A. A. Zatsarinnyy

{"title":"神经网络图像识别技术的脆弱性分析","authors":"A. V. Trusov, E. E. Limonova, V. V. Arlazarov, A. A. Zatsarinnyy","doi":"10.1134/s0361768823100079","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>The problem of vulnerability of artificial intelligence technologies based on neural networks is considered. It is shown that the use of neural networks generates a lot of vulnerabilities. Examples of such vulnerabilities are demonstrated, such as incorrect classification of images containing adversarial noise or patches, failure of recognition systems in the presence of special patterns in the image, including those applied to objects in the real world, training data poisoning, etc. Based on the analysis, the need to improve the security of artificial intelligence technologies is shown, and some considerations that contribute to this improvement are discussed.</p>","PeriodicalId":54555,"journal":{"name":"Programming and Computer Software","volume":null,"pages":null},"PeriodicalIF":0.7000,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Analysis of Vulnerabilities of Neural Network Image Recognition Technologies\",\"authors\":\"A. V. Trusov, E. E. Limonova, V. V. Arlazarov, A. A. Zatsarinnyy\",\"doi\":\"10.1134/s0361768823100079\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<h3 data-test=\\\"abstract-sub-heading\\\">Abstract</h3><p>The problem of vulnerability of artificial intelligence technologies based on neural networks is considered. It is shown that the use of neural networks generates a lot of vulnerabilities. Examples of such vulnerabilities are demonstrated, such as incorrect classification of images containing adversarial noise or patches, failure of recognition systems in the presence of special patterns in the image, including those applied to objects in the real world, training data poisoning, etc. Based on the analysis, the need to improve the security of artificial intelligence technologies is shown, and some considerations that contribute to this improvement are discussed.</p>\",\"PeriodicalId\":54555,\"journal\":{\"name\":\"Programming and Computer Software\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.7000,\"publicationDate\":\"2024-03-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Programming and Computer Software\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1134/s0361768823100079\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Programming and Computer Software","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1134/s0361768823100079","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}

引用次数: 0

摘要

摘要研究了基于神经网络的人工智能技术的脆弱性问题。研究表明，神经网络的使用会产生许多漏洞。举例说明了这些漏洞，如对含有对抗噪声或补丁的图像进行错误分类、在图像中存在特殊模式（包括应用于现实世界中物体的模式）时识别系统失效、训练数据中毒等。在分析的基础上，说明了提高人工智能技术安全性的必要性，并讨论了有助于提高安全性的一些考虑因素。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Analysis of Vulnerabilities of Neural Network Image Recognition Technologies

查看原文本刊更多论文

Analysis of Vulnerabilities of Neural Network Image Recognition Technologies

Abstract

The problem of vulnerability of artificial intelligence technologies based on neural networks is considered. It is shown that the use of neural networks generates a lot of vulnerabilities. Examples of such vulnerabilities are demonstrated, such as incorrect classification of images containing adversarial noise or patches, failure of recognition systems in the presence of special patterns in the image, including those applied to objects in the real world, training data poisoning, etc. Based on the analysis, the need to improve the security of artificial intelligence technologies is shown, and some considerations that contribute to this improvement are discussed.

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

Programming and Computer Software 工程技术-计算机：软件工程

CiteScore

1.60

自引率

28.60%

发文量

审稿时长

>12 weeks

期刊介绍： Programming and Computer Software is a peer reviewed journal devoted to problems in all areas of computer science: operating systems, compiler technology, software engineering, artificial intelligence, etc.