SoK: A Study of the Security on Voice Processing Systems

TL;DR

This paper reviews the evolving landscape of security threats to voice processing systems, classifies various attacks, and discusses the need for improved defenses in the context of growing privacy and safety concerns.

Contribution

It provides a comprehensive classification of attacks on voice processing systems and highlights the security challenges posed by modern machine learning-based approaches.

Findings

Increased complexity and variety of attacks on VPS.

Shift from untargeted to targeted attacks over time.

Highlighting the security vulnerabilities of neural network-based systems.

Abstract

As the use of Voice Processing Systems (VPS) continues to become more prevalent in our daily lives through the increased reliance on applications such as commercial voice recognition devices as well as major text-to-speech software, the attacks on these systems are increasingly complex, varied, and constantly evolving. With the use cases for VPS rapidly growing into new spaces and purposes, the potential consequences regarding privacy are increasingly more dangerous. In addition, the growing number and increased practicality of over-the-air attacks have made system failures much more probable. In this paper, we will identify and classify an arrangement of unique attacks on voice processing systems. Over the years research has been moving from specialized, untargeted attacks that result in the malfunction of systems and the denial of services to more general, targeted attacks that can force an outcome controlled by an adversary. The current and most frequently used machine learning systems and deep neural networks, which are at the core of modern voice processing systems, were built with a focus on performance and scalability rather than security. Therefore, it is critical for us to reassess the developing voice processing landscape and to identify the state of current attacks and defenses so that we may suggest future developments and theoretical improvements.