# Securing Voice Authentication Applications Against Targeted Data Poisoning

arXiv: https://arxiv.org/abs/2406.17277 · HTML: https://mlsanity.com/paper/2406.17277/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Audio jailbreaks and speech backdoors, one of 12 directions in LLM safety and security.
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Placed in

- LLM safety and security / [Audio jailbreaks and speech backdoors](https://mlsanity.com/safety/audio-jailbreaks-and-speech-backdoors/)

## Builds on (most cited first, 7 of 7)

- [Adversarial Attacks and Defenses in Images, Graphs and Text: A Review](https://mlsanity.com/paper/1909.08072/) (2019)
- [Sever: A Robust Meta-Algorithm for Stochastic Optimization](https://mlsanity.com/paper/1803.02815/) (2018)
- [Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff](https://mlsanity.com/paper/2011.09527/) (2020)
- [Deep Speaker: an End-to-End Neural Speaker Embedding System](https://mlsanity.com/paper/1705.02304/) (2017)
- [Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection](https://mlsanity.com/paper/1802.03041/) (2018)
- [Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks](https://mlsanity.com/paper/2110.06904/) (2021)
- [Defend Data Poisoning Attacks on Voice Authentication](https://mlsanity.com/paper/2209.04547/) (2022)

## Built on by (most cited first, 2 of 2)

- [A Survey of Threats Against Voice Authentication and Anti-Spoofing Systems](https://mlsanity.com/paper/2508.16843/) (2025)
- [Audio Physical Dynamics Inspired Deepfake Detection for Voice Authentication Systems](https://mlsanity.com/paper/2512.06040/) (2025)

## Abstract (arXiv)

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.