mlsanityData to 14 Oct 2026

SoK: A Study of the Security on Voice Processing Systems

arXiv 2112.13144 ↗First posted 24 Dec 2021cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 24 Dec 2021.

Builds on

24 of 36 references.

References · 24

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  4. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  5. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  6. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  7. 2017One pixel attack for fooling deep neural networkscited by 582
  8. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  9. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  10. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 225
  11. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  12. 2018Stealing Hyperparameters in Machine Learningcited by 118
12 more
  1. 2018Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attackscited by 81
  2. 2017DolphinAtack: Inaudible Voice Commandscited by 69
  3. 2019Hear "No Evil", See "Kenansville": Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systemscited by 38
  4. 2018Characterizing Audio Adversarial Examples Using Temporal Dependencycited by 36
  5. 2019Practical Hidden Voice Attacks against Speech and Speaker Recognition Systemscited by 36
  6. 2019SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systemscited by 34
  7. 2019LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applicationscited by 15
  8. 2019Perceptual Based Adversarial Audio Attackscited by 13
  9. 2020Identifying Audio Adversarial Examples via Anomalous Pattern Detectioncited by 9
  10. 2017Inaudible Voice Commandscited by 6
  11. 2021SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systemscited by 4
  12. 2019Understanding the Effectiveness of Ultrasonic Microphone Jammercited by 3

Built on by

Not cited yet.