{"title":"Continuous Speaker Authentication when Using Network Administrator Virtual Assistant","authors":"Sh.I. Khanbekov, Alexander Zakharov","doi":"10.1109/SmartIndustryCon57312.2023.10110730","DOIUrl":null,"url":null,"abstract":"In this paper we introduce the continuous authentication system for voice‑controlled network administrator virtual assistant. While voice control is a promising technology in such fields as Internet of Things, smart home systems and voice assistant applications, the voice transmission channel is vulnerable to a number of threats which bypass the standard technique of one‑time authentication. The efficiency of the proposed system is achieved by analyzing the physical characteristics of inbound speech signal in a form of mel‑frequency cepstral coefficients and hierarchically distinguishing the voice commands according to their possible negative impact on information security state. The considered continuous authentication system can be deployed in a local environment on a low‑performance device while maintaining acceptable accuracy rates.","PeriodicalId":157877,"journal":{"name":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 International Russian Smart Industry Conference (SmartIndustryCon)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SmartIndustryCon57312.2023.10110730","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper we introduce the continuous authentication system for voice‑controlled network administrator virtual assistant. While voice control is a promising technology in such fields as Internet of Things, smart home systems and voice assistant applications, the voice transmission channel is vulnerable to a number of threats which bypass the standard technique of one‑time authentication. The efficiency of the proposed system is achieved by analyzing the physical characteristics of inbound speech signal in a form of mel‑frequency cepstral coefficients and hierarchically distinguishing the voice commands according to their possible negative impact on information security state. The considered continuous authentication system can be deployed in a local environment on a low‑performance device while maintaining acceptable accuracy rates.