# Attacking Speaker Recognition With Deep Generative Models

arXiv: https://arxiv.org/abs/1801.02384 · HTML: https://mlsanity.com/paper/1801.02384/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jan 2018.

## Built on by (most cited first, 1 of 1)

- [Attacks as Defenses: Designing Robust Audio CAPTCHAs Using Attacks on Automatic Speech Recognition Systems](https://mlsanity.com/paper/2203.05408/) (2022)

## Abstract (arXiv)

In this paper we investigate the ability of generative adversarial networks (GANs) to synthesize spoofing attacks on modern speaker recognition systems. We first show that samples generated with SampleRNN and WaveNet are unable to fool a CNN-based speaker recognition system. We propose a modification of the Wasserstein GAN objective function to make use of data that is real but not from the class being learned. Our semi-supervised learning method is able to perform both targeted and untargeted attacks, raising questions related to security in speaker authentication systems.