An Overview of Vulnerabilities of Voice Controlled Systems

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.

[1]  Christian Poellabauer,et al.  Crafting Adversarial Examples For Speech Paralinguistics Applications , 2017, ArXiv.

[2]  Alex X. Liu,et al.  The Insecurity of Home Digital Voice Assistants - Amazon Alexa as a Case Study , 2017, ArXiv.

[3]  C. Kasmi,et al.  IEMI Threats for Information Security: Remote Command Injection on Modern Smartphones , 2015, IEEE Transactions on Electromagnetic Compatibility.

[4]  David A. Wagner,et al.  Audio Adversarial Examples: Targeted Attacks on Speech-to-Text , 2018, 2018 IEEE Security and Privacy Workshops (SPW).

[5]  Micah Sherr,et al.  Hidden Voice Commands , 2016, USENIX Security Symposium.

[6]  Mani B. Srivastava,et al.  Did you hear that? Adversarial Examples Against Automatic Speech Recognition , 2018, ArXiv.

[7]  Moustapha Cissé,et al.  Houdini: Fooling Deep Structured Prediction Models , 2017, ArXiv.

[8]  Aziz Mohaisen,et al.  You Can Hear But You Cannot Steal: Defending Against Voice Impersonation Attacks on Smartphones , 2017, 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS).

[9]  Micah Sherr,et al.  Cocaine Noodles: Exploiting the Gap between Human and Machine Speech Recognition , 2015, WOOT.

[10]  Erich Elsen,et al.  Deep Speech: Scaling up end-to-end speech recognition , 2014, ArXiv.

[11]  Xiangyu Liu,et al.  Your Voice Assistant is Mine: How to Abuse Speakers to Steal Information and Control Your Phone , 2014, SPSM@CCS.

[12]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[13]  Kang G. Shin,et al.  Continuous Authentication for Voice Assistants , 2017, MobiCom.

[14]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[15]  Yuqiong Sun,et al.  AuDroid: Preventing Attacks on Audio Channels in Mobile Devices , 2015, ACSAC.

[16]  Wenke Lee,et al.  A11y Attacks: Exploiting Accessibility in Operating Systems , 2014, CCS.

[17]  Constantinos Patsakis,et al.  Monkey Says, Monkey Does: Security and Privacy on Voice Assistants , 2017, IEEE Access.

[18]  Wenyuan Xu,et al.  DolphinAttack: Inaudible Voice Commands , 2017, CCS.