Remote User Authentication Using a Voice Authentication System

Kaman, Shilpa; Swetha, K.; Akram, Syed; Varaprasad, G.

doi:10.1080/19393555.2013.801539

Cited by 8 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Scholars have done a lot of optimizations based on I-Vector, including Linear Discriminant Analysis (LDA), Linear Predictive Discriminant analysis (PLDA), Metric Learning, and so on [3]. X-Vector is based on Deep Neural Network (DNN) [9], [13], which can abstract voice features from a large number of samples. DNN can accurately obtain a user's voiceprint information by using a speech with about 10 seconds and can strongly resist noise interference with high robustness.…”

Section: A Voiceprint Recognitionmentioning

confidence: 99%

LiVoAuth: Liveness Detection in Voiceprint Authentication With Random Challenges and Detection Modes

Zhang

Yan

Wang

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Voiceprint authentication provides great convenience to users in many application scenarios. However, it easily suffers from spoofing attacks including speech synthesis, speech conversion and speech replay. Liveness detection is an effective way to resist these attacks. But existing methods suffer from many disadvantages, such as extra deployment costs due to precise data collection, environmental disturbance, high computational overhead and operational complexity. A uniform platform that can offer Voiceprint Authentication as a Service (VAaS) over the cloud is also lacked. Hence, it is imperative to design an economic and effective method for liveness detection in voiceprint authentication. In this paper, we propose a novel liveness detection method named LiVoAuth for voiceprint authentication. It applies a randomly generated vector sequence as Liveness Detection Mode (LDM), corresponding to a random challenge code used for authentication. We implement LiVoAuth and conduct a series of user studies to evaluate its performance in terms of accuracy, stability, efficiency, security, and user acceptance. Experimental results demonstrate its advantages compared with cuttingedge methods.

show abstract

Section: A Voiceprint Recognitionmentioning

confidence: 99%

LiVoAuth: Liveness Detection in Voiceprint Authentication With Random Challenges and Detection Modes

Zhang

Yan

Wang

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…There are many methods proposed to perform morphing detection. In order to detect Face Morphing Forgery (FMF) attacks, in [96], Neubert et al proposed a novel three-fold definition (visual, biometric and forensic qualities) for the quality of morphed images to improve morphing detection. In addition, Neubert et al introduced a novel FMF realization method in order to improve visual and biometric quality.…”

Section: Replay Attack Defensementioning

confidence: 99%

“…In addition, voice recognition is often combined with other technologies to realize liveness detection and enhance system security. For example, Kaman et al [96] designed a practical authentication system for remote online banking. When a user is trying to login, a remote server will give a phone call to the user and ask he or she to record voice.…”

Section: Replay Attack Defensementioning

confidence: 99%

Attacks and defenses in user authentication systems: A survey

Wang

Yan

Zhang

et al. 2021

Journal of Network and Computer Applications

View full text Add to dashboard Cite

“…This ranges from the use of physical features (including voiceprints, fingerprints and iris recognition) to behavioural features (including gait and handwriting recognition). Biometrics is inherently difficult to copy, share and distribute; difficult to forge; and importantly cannot be lost or forgotten because the individual has to be physically present (Kaman et al, 2013;Tassabehji and Kamala, 2012). Keystroke dynamics, a type of biometrics which also uses a behavioural trait unique to a user, is a technology that ensures that the user, post-authentication, is indeed the user authenticated (Pisani and Lorena, 2013).…”

Section: User Authenticationmentioning

confidence: 99%

Investigating the possibility to use differentiated authentication based on risk profiling to secure online banking

Butler

2015

Information &Amp; Computer Security

View full text Add to dashboard Cite

Purpose – The purpose of this paper was to determine factors that could be used to create different authentication requirements for diverse online banking customers based on their risk profile. Online security remains a challenge to ensure safe transacting on the Internet. User authentication, a human-centric process, is regarded as the basis of computer security and hence secure access to online banking services. The increased use of technology to enforce additional actions has the ability to improve the quality of authentication and hence online security, but often at the expense of usability. The objective of this study was to determine factors that could be used to create different authentication requirements for diverse online banking customers based on their risk profile. Design/methodology/approach – A web-based survey was designed to determine online consumers’ competence resecure online behaviour, and this was used to quantify the online behaviour as more or less secure. The browsers used by consumers as well as their demographical data were correlated with the security profile of respondents to test for any significant variance in practice that could inform differentiated authentication. Findings – A statistical difference between behaviours based on some of the dependant variables was evident from the analysis. Based on the results, a case could be made to have different authentication methods for online banking customers based on both their browser selected (before individual identification) as well as demographical data (after identification) to ensure a safer online environment. Originality/value – The research can be used by the financial services sector to improve online security, where required, without necessarily reducing usability for more “security inclined” customers.

show abstract

Remote User Authentication Using a Voice Authentication System

Cited by 8 publications

References 1 publication

LiVoAuth: Liveness Detection in Voiceprint Authentication With Random Challenges and Detection Modes

LiVoAuth: Liveness Detection in Voiceprint Authentication With Random Challenges and Detection Modes

Attacks and defenses in user authentication systems: A survey

Investigating the possibility to use differentiated authentication based on risk profiling to secure online banking

Contact Info

Product

Resources

About