Perceived severity of vulnerability in cybersecurity: cross linguistic variegation

2022 IEEE International Carnahan Conference on Security Technology (ICCST) Pub Date : 2022-09-07 DOI:10.1109/ICCST52959.2022.9896488

Wiktor Sedkowski, Karol Bierczyński

{"title":"Perceived severity of vulnerability in cybersecurity: cross linguistic variegation","authors":"Wiktor Sedkowski, Karol Bierczyński","doi":"10.1109/ICCST52959.2022.9896488","DOIUrl":null,"url":null,"abstract":"The emergence of artificial intelligence [AI] , computer vision, and speech recognition systems have made significant growth in all areas of human life including cybersecurity. Multiple cybersecurity companies are trying to leverage AI to help combat cyberattacks as AI and machine learning can faster and cheaper monitor for any suspicious activity in the network, informing security specialists and network administrators only in case of a true emergency. As modern AI-powered systems are cooperating with human users by not only providing raw reports but also producing information based on text generation algorithms and text-to-speech functions, it is essential to ensure that this sensitive, security related information is not biased. In this pilot study, we are trying to showcase the problem of the perceived severity of a vulnerability by recipients speaking different native languages. Also, we are trying to answer the following question: how should an AI system present the information in order for the user to correctly understand the severity of the finding?","PeriodicalId":364791,"journal":{"name":"2022 IEEE International Carnahan Conference on Security Technology (ICCST)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Carnahan Conference on Security Technology (ICCST)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCST52959.2022.9896488","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

Abstract

The emergence of artificial intelligence [AI] , computer vision, and speech recognition systems have made significant growth in all areas of human life including cybersecurity. Multiple cybersecurity companies are trying to leverage AI to help combat cyberattacks as AI and machine learning can faster and cheaper monitor for any suspicious activity in the network, informing security specialists and network administrators only in case of a true emergency. As modern AI-powered systems are cooperating with human users by not only providing raw reports but also producing information based on text generation algorithms and text-to-speech functions, it is essential to ensure that this sensitive, security related information is not biased. In this pilot study, we are trying to showcase the problem of the perceived severity of a vulnerability by recipients speaking different native languages. Also, we are trying to answer the following question: how should an AI system present the information in order for the user to correctly understand the severity of the finding?

查看原文本刊更多论文

网络安全脆弱性的感知严重性:跨语言差异

人工智能(AI)、计算机视觉和语音识别系统的出现，在包括网络安全在内的人类生活的各个领域取得了显著增长。多家网络安全公司正试图利用人工智能来帮助打击网络攻击，因为人工智能和机器学习可以更快、更便宜地监控网络中的任何可疑活动，只有在真正的紧急情况下才通知安全专家和网络管理员。由于现代人工智能系统不仅提供原始报告，而且还基于文本生成算法和文本到语音功能生成信息，因此必须确保这些敏感的、与安全相关的信息不存在偏见。在这项初步研究中，我们试图展示说不同母语的接受者对脆弱性严重性的感知问题。此外，我们试图回答以下问题:AI系统应该如何呈现信息，以便用户正确理解发现的严重性?

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2022 IEEE International Carnahan Conference on Security Technology (ICCST)

自引率

0.00%

发文量