mlsanityData to 7 Oct 2026

Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning

arXiv 2211.09273 ↗First posted 17 Nov 2022cs.LG cs.CR cs.SDcited by 2

Not on the map. Why?

Abstract (arXiv)

Smart speaker voice assistants (VAs) such as Amazon Echo and Google Home have been widely adopted due to their seamless integration with smart home devices and the Internet of Things (IoT) technologies. These VA services raise privacy concerns, especially due to their access to our speech. This work considers one such use case: the unaccountable and unauthorized surveillance of a user's emotion via speech emotion recognition (SER). This paper presents DARE-GP, a solution that creates additive noise to mask users' emotional information while preserving the transcription-relevant portions of their speech. DARE-GP does this by using a constrained genetic programming approach to learn the spectral frequency traits that depict target users' emotional content, and then generating a universal adversarial audio perturbation that provides this privacy protection. Unlike existing works, DARE-GP provides: a) real-time protection of previously unheard utterances, b) against previously unseen black-box SER classifiers, c) while protecting speech transcription, and d) does so in a realistic, acoustic environment. Further, this evasion is robust against defenses employed by a knowledgeable adversary. The evaluations in this work culminate with acoustic evaluations against two off-the-shelf commercial smart speakers using a small-form-factor (raspberry pi) integrated with a wake-word system to evaluate the efficacy of its real-world, real-time deployment.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 30 of its 156 references that are in the map. First posted on arXiv 17 Nov 2022.

Builds on

30 of 156 references.

References · 30

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  6. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  7. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  8. 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
  9. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 118
  10. 2020Investigating Bias and Fairness in Facial Expression Recognitioncited by 87
  11. 2020Towards Learning a Universal Non-Semantic Representation of Speechcited by 84
  12. 2017DolphinAtack: Inaudible Voice Commandscited by 65
18 more
  1. 2018Did you hear that? Adversarial Examples Against Automatic Speech Recognitioncited by 48
  2. 2020SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systemscited by 46
  3. 2018Targeted Adversarial Examples for Black Box Audio Systemscited by 41
  4. 2021WaveGuard: Understanding and Mitigating Audio Adversarial Examplescited by 39
  5. 2020Speaker anonymisation using the McAdams coefficientcited by 38
  6. 2020Privacy-preserving Voice Analysis via Disentangled Representationscited by 24
  7. 2021Multimodal Emotion Recognition with High-level Speech and Text Featurescited by 20
  8. 2019Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systemscited by 16
  9. 2021Speech Emotion Recognition with Multiscale Area Attention and Data Augmentationcited by 12
  10. 2019Universal Adversarial Audio Perturbationscited by 11
  11. 2021Stagnation Detection with Randomized Local Searchcited by 11
  12. 2022Bias and Fairness on Multimodal Emotion Detection Algorithmscited by 10
  13. 2020Detecting Emotion Primitives from Speech and their use in discerning Categorical Emotionscited by 8
  14. 2019Emotionless: Privacy-Preserving Speech Analysis for Voice Assistantscited by 6
  15. 2020Paralinguistic Privacy Protection at the Edgecited by 5
  16. 2019Emotion Filtering at the Edgecited by 4
  17. 2021DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensingcited by 4
  18. 2021Kryptonite: An Adversarial Attack Using Regional Focuscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Exploring Audio Editing Features as User-Centric Privacy Defenses Against Large Language Model(LLM) Based Emotion Inference Attackscited by 0
  2. 2026Unrequited Emotions: Investigating the Gaps in Motivation and Practice in Speech Emotion Recognition Researchcited by 0