Total Downloads: 47 , 1
An Optimized and Privacy-Preserving System Architecture for Effective Voice Authentication over Wireless Network
Aniruddha Deka1, Debashis Dev Misra2
1Dr. Aniruddha Deka, Associate Professor, Department of Computer Science and Engineering, Assam Down Town University, Guwahati (Assam), India.
2Dr. Debashis Dev Misra, Associate Professor, Department of Computer Science and Engineering, Assam Down Town University, Guwahati (Assam), India.
Manuscript received on 13 July 2023 | Revised Manuscript received on 18 July 2023 | Manuscript Accepted on 15 September 2023 | Manuscript published on 30 September 2023 | PP: 1-9 | Volume-12 Issue-3, September 2023 | Retrieval Number: 100.1/ijrte.C78620912323 | DOI: 10.35940/ijrte.C7862.0912323
Open Access | Editorial and Publishing Policies | Cite | Zenodo | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The speaker authentication systems assist in determining the identity of a speaker in audio through distinctive voice characteristics. Accurate speaker authentication over wireless networks is becoming more challenging due to phishing attacks on the network. Multiple types of speech authentication models have been constructed for use in various applications where voice authentication is a primary focus for user identity verification. However, existing voice authentication models have some limitations related to accuracy and phishing attacks in real-time over wireless networks. In research, an optimised and privacypreserving system architecture for effective speaker authentication over a wireless network has been proposed to accurately identify the speaker’s voice in real-time and prevent phishing attacks over the network with greater accuracy. The proposed system achieved excellent performance metrics, with measured accuracy, precision, and recall, as well as an F1 score of 98.91%, 96.43%, 95.37%, and 97.99%, respectively. The measured training losses at epochs 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, and 100 were 2.4, 2.1, 1.8, 1.5, 1.2, 0.9, 0.6, 0.3, 0.3, 0.3, and 0.2, respectively. Additionally, the measured testing losses for epochs 0, 10, 20, 30, 40, 50, 60, 70, 80, 90, and 100 were 2.2, 2.0, 1.5, 1.4, 1.1, 0.8, 0.8, 0.7, 0.4, 0.1, and 0.1, respectively. Voice authentication over wireless networks is a significant concern due to various phishing attacks and inaccuracies in voice identification. Therefore, this requires huge attention for further research in this field to develop less computationally complex speech authentication systems
Keywords: CNN, LSTM, Speaker Authentication, Privacy-Preserving, Phishing Assaults, Wireless Network.
Scope of the Article: Network Protocols & Wireless Networks