An Overview of Vulnerabilities of Voice Controlled Systems

Abstract

Over the last few years, a rapidly increasing number of Internet-of-Things (IoT) systems that adopt voice as the primary user input have emerged. These systems have been shown to be vulnerable to various types of voice spoofing attacks. However, how exactly these techniques differ or relate to each other has not been extensively studied. In this paper, we provide a survey of recent attack and defense techniques for voice controlled systems and propose a classification of these techniques. We also discuss the need for a universal defense strategy that protects a system from various types of attacks.

1st International Workshop on Security and Privacy for the Internet-of-Things (IoTSec)

References in corpus (4)

• Did you hear that? Adversarial Examples Against Automatic Speech Recognition
• Houdini: Fooling Deep Structured Prediction Models
• The Insecurity of Home Digital Voice Assistants -- Amazon Alexa as a Case Study
• Continuous Authentication for Voice Assistants

Cited by in corpus (7)

• Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness
• Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method
• Protecting Voice Controlled Systems Using Sound Source Identification Based on Acoustic Cues
• Universal adversarial examples in speech command classification
• Real-Time Adversarial Attacks
• ReMASC: Realistic Replay Attack Corpus for Voice Controlled Systems
• On the human evaluation of audio adversarial examples