國立虎尾科技大學 |

Enhancing Privacy and Security for Voice Assistant Systems.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Enhancing Privacy and Security for Voice Assistant Systems./
作者:	Tran, Bang Quanghai.
面頁冊數:	1 online resource (117 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
Contained By:	Dissertations Abstracts International85-03B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798380330688

Enhancing Privacy and Security for Voice Assistant Systems.
Tran, Bang Quanghai.

Enhancing Privacy and Security for Voice Assistant Systems. - 1 online resource (117 pages)

Source: Dissertations Abstracts International, Volume: 85-03, Section: B.

Thesis (Ph.D.)--University of Massachusetts Boston, 2023.

Includes bibliographical references

The rapid proliferation of Voice Assistant (VA) devices such as Amazon's Alexa, Google Home, and Apple's Siri has transformed how we interact with technology in our daily lives. These devices provide users with hands-free access to various services, from weather forecasts and news updates to music streaming and home automation. However, the convenience and utility of VA devices come with a trade-off regarding privacy and security. Researchers have noted that voice assistant devices may be vulnerable to attacks by malicious actors, who could take control of the device or use it to access other devices on a user's network. Besides that, leaking the biophysical status of the users from voice signals and being profiled by Voice Service Providers (VSP) are recent concerns as the advances of Deep Learning techniques as well as Natural Language Processing (NLP). This dissertation first presents a solution to enhance the security of VA devices. Our proposed defending system on the VA devices can against both voice replay and injection attacks without any additional devices or any extra user's effort. Specifically, we use both voice and wireless data to verify the correlation between the user's presence and voice commands, then finally detect the attacks.Secondly, this dissertation proposes an anonymity scheme on VA devices to protecting users' voice data from being linked to their accounts by the VSP. Our proposed scheme aims to mix the queries from multiple VA users' devices, hiding the source of queries and hiding the relay's real queries. To achieve effective anonymity, the anonymizer is equipped with a proposed privacy-preserving pattern matching scheme, which is run with the help of a semi-trusted server and is used to find the most effective relay for the requester based on their pattern similarity.Thirdly, we introduce a framework VPASS, that supports managing personalized privacy requirements for VA systems. Specifically, we propose mechanisms to quantify two key aspects: the amount of information disclosure and the level of privacy sensitivity each voice command has. Our mechanisms employ deep learning techniques for natural language processing and can accurately detect privacy-sensitive commands based on an individual's prior history of VAS interaction. Finally, VPASS generates monthly reports or immediate privacy alerts based on the privacy policies pre-defined by users.Lastly, we demonstrate the vulnerable of detecting sleepiness status of VAS user from human speech. Our proposed an attention-based convolutional neural network (CNN) model classifies sleepy and non-sleepy states. We incorporate an attention mechanism to obtain explainable results from the deep learning model on the relevance of speech responses to sleepiness detection. We also show that the embedded attention layers of our proposed model improves the detection accuracy in different cases of inputs. The attention mechanism enables our model to take all responses as one input, simplifying the data pre-processing and identifying the relevant speech responses to sleepiness detection.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380330688Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

PrivacyIndex Terms--Genre/Form:

554714
Electronic books.

Enhancing Privacy and Security for Voice Assistant Systems.
LDR:04463ntm a22003977 4500 001 1143809
005 20240517104958.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380330688
035 $a (MiAaPQ)AAI30531354
035 $a AAI30531354
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Tran, Bang Quanghai. $3 1468602
245 1 0 $a Enhancing Privacy and Security for Voice Assistant Systems.
264 0 $c 2023
300 $a 1 online resource (117 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
500 $a Advisor: Liang, Xiaohui.
502 $a Thesis (Ph.D.)--University of Massachusetts Boston, 2023.
504 $a Includes bibliographical references
520 $a The rapid proliferation of Voice Assistant (VA) devices such as Amazon's Alexa, Google Home, and Apple's Siri has transformed how we interact with technology in our daily lives. These devices provide users with hands-free access to various services, from weather forecasts and news updates to music streaming and home automation. However, the convenience and utility of VA devices come with a trade-off regarding privacy and security. Researchers have noted that voice assistant devices may be vulnerable to attacks by malicious actors, who could take control of the device or use it to access other devices on a user's network. Besides that, leaking the biophysical status of the users from voice signals and being profiled by Voice Service Providers (VSP) are recent concerns as the advances of Deep Learning techniques as well as Natural Language Processing (NLP). This dissertation first presents a solution to enhance the security of VA devices. Our proposed defending system on the VA devices can against both voice replay and injection attacks without any additional devices or any extra user's effort. Specifically, we use both voice and wireless data to verify the correlation between the user's presence and voice commands, then finally detect the attacks.Secondly, this dissertation proposes an anonymity scheme on VA devices to protecting users' voice data from being linked to their accounts by the VSP. Our proposed scheme aims to mix the queries from multiple VA users' devices, hiding the source of queries and hiding the relay's real queries. To achieve effective anonymity, the anonymizer is equipped with a proposed privacy-preserving pattern matching scheme, which is run with the help of a semi-trusted server and is used to find the most effective relay for the requester based on their pattern similarity.Thirdly, we introduce a framework VPASS, that supports managing personalized privacy requirements for VA systems. Specifically, we propose mechanisms to quantify two key aspects: the amount of information disclosure and the level of privacy sensitivity each voice command has. Our mechanisms employ deep learning techniques for natural language processing and can accurately detect privacy-sensitive commands based on an individual's prior history of VAS interaction. Finally, VPASS generates monthly reports or immediate privacy alerts based on the privacy policies pre-defined by users.Lastly, we demonstrate the vulnerable of detecting sleepiness status of VAS user from human speech. Our proposed an attention-based convolutional neural network (CNN) model classifies sleepy and non-sleepy states. We incorporate an attention mechanism to obtain explainable results from the deep learning model on the relevance of speech responses to sleepiness detection. We also show that the embedded attention layers of our proposed model improves the detection accuracy in different cases of inputs. The attention mechanism enables our model to take all responses as one input, simplifying the data pre-processing and identifying the relevant speech responses to sleepiness detection.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Computer engineering. $3 569006
650 4 $a Electrical engineering. $3 596380
653 $a Privacy
653 $a Security
653 $a Biophysical status
653 $a Voice Service Providers
653 $a Wireless data
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0544
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Massachusetts Boston. $b Computer Science (PhD). $3 1190753
773 0 $t Dissertations Abstracts International $g 85-03B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30531354 $z click for full text (PQDT)