"Hello, It's Me": Deep Learning-based Speech Synthesis Attacks in the Real World

TL;DR

This paper investigates the real-world risks of deep learning-based speech synthesis attacks, demonstrating their effectiveness against humans and voice recognition systems, and highlighting the inadequacy of current defenses.

Contribution

It provides a comprehensive experimental analysis of speech synthesis attack impacts on humans and machines, revealing vulnerabilities and the need for improved protections.

Findings

Synthetic speech can reliably fool humans and machines

Existing defenses against synthetic speech are insufficient

The study underscores the urgency for new protective measures

Abstract

Advances in deep learning have introduced a new wave of voice synthesis tools, capable of producing audio that sounds as if spoken by a target speaker. If successful, such tools in the wrong hands will enable a range of powerful attacks against both humans and software systems (aka machines). This paper documents efforts and findings from a comprehensive experimental study on the impact of deep-learning based speech synthesis attacks on both human listeners and machines such as speaker recognition and voice-signin systems. We find that both humans and machines can be reliably fooled by synthetic speech and that existing defenses against synthesized speech fall short. These findings highlight the need to raise awareness and develop new protections against synthetic speech for both humans and machines.