mlsanityData to 7 Oct 2026

VSVC: Backdoor attack against Keyword Spotting based on Voiceprint Selection and Voice Conversion

arXiv 2212.10103 ↗First posted 20 Dec 2022cs.SD cs.AI cs.CRcited by 6

On the map: LLM safety and security → Audio jailbreaks and speech backdoors

Abstract (arXiv)

Keyword spotting (KWS) based on deep neural networks (DNNs) has achieved massive success in voice control scenarios. However, training of such DNN-based KWS systems often requires significant data and hardware resources. Manufacturers often entrust this process to a third-party platform. This makes the training process uncontrollable, where attackers can implant backdoors in the model by manipulating third-party training data. An effective backdoor attack can force the model to make specified judgments under certain conditions, i.e., triggers. In this paper, we design a backdoor attack scheme based on Voiceprint Selection and Voice Conversion, abbreviated as VSVC. Experimental results demonstrated that VSVC is feasible to achieve an average attack success rate close to 97% in four victim models when poisoning less than 1% of the training data.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Audio jailbreaks and speech backdoors, one of 12 directions in LLM safety and security. Builds on 19 of its 38 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

19 of 38 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Wide Residual Networkscited by 3,057
  4. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  5. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
  6. 2020Backdoor Learning: A Surveycited by 412
  7. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  8. 2020Invisible Backdoor Attack with Sample-Specific Triggerscited by 338
  9. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
  10. 2021Rethinking the Backdoor Attacks' Triggers: A Frequency Perspectivecited by 155
  11. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 147
  12. 2021Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitutioncited by 85
7 more
  1. 2021Backdoor Attack in the Physical Worldcited by 82
  2. 2020Backdoor Attack against Speaker Verificationcited by 62
  3. 2021StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversioncited by 57
  4. 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
  5. 2021Can You Hear It? Backdoor Attacks via Ultrasonic Triggerscited by 41
  6. 2022Few-Shot Backdoor Attacks on Visual Object Trackingcited by 35
  7. 2019Adversarial Audio: A New Information Hiding Method and Backdoor for DNN-based Speech Recognition Modelscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2023Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversioncited by 9
  2. 2023FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledgecited by 9
  3. 2024Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognitioncited by 5
  4. 2024EmoAttack: Utilizing Emotional Voice Conversion for Speech Backdoor Attacks on Deep Speech Classification Modelscited by 2
  5. 2025SPBA: Utilizing Speech Large Language Model for Backdoor Attacks on Speech Classification Modelscited by 0
  6. 2026Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attackcited by 0