Securing Voice Authentication Applications Against Targeted Data Poisoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mohammadi, Alireza, Sood, Keshav, Nazari, Asef, Thiruvady, Dhananjay
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929522149949440
author Mohammadi, Alireza
Sood, Keshav
Nazari, Asef
Thiruvady, Dhananjay
author_facet Mohammadi, Alireza
Sood, Keshav
Nazari, Asef
Thiruvady, Dhananjay
contents Deep neural network-based voice authentication systems are promising biometric verification techniques that uniquely identify biological characteristics to verify a user. However, they are particularly susceptible to targeted data poisoning attacks, where attackers replace legitimate users' utterances with their own. We propose an enhanced framework using realworld datasets considering realistic attack scenarios. The results show that the proposed approach is robust, providing accurate authentications even when only a small fraction (5% of the dataset) is poisoned.
format Preprint
id arxiv_https___arxiv_org_abs_2406_17277
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Securing Voice Authentication Applications Against Targeted Data Poisoning
Mohammadi, Alireza
Sood, Keshav
Nazari, Asef
Thiruvady, Dhananjay
Cryptography and Security
Deep neural network-based voice authentication systems are promising biometric verification techniques that uniquely identify biological characteristics to verify a user. However, they are particularly susceptible to targeted data poisoning attacks, where attackers replace legitimate users' utterances with their own. We propose an enhanced framework using realworld datasets considering realistic attack scenarios. The results show that the proposed approach is robust, providing accurate authentications even when only a small fraction (5% of the dataset) is poisoned.
title Securing Voice Authentication Applications Against Targeted Data Poisoning
topic Cryptography and Security
url https://arxiv.org/abs/2406.17277