mlsanityData to 14 Oct 2026

Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition

arXiv 2203.04696 ↗First posted 9 Mar 2022cs.SD cs.LG eess.AScited by 6

Not on the map. Why?

Abstract (arXiv)

Due to the development of machine learning and speech processing, speech emotion recognition has been a popular research topic in recent years. However, the speech data cannot be protected when it is uploaded and processed on servers in the internet-of-things applications of speech emotion recognition. Furthermore, deep neural networks have proven to be vulnerable to human-indistinguishable adversarial perturbations. The adversarial attacks generated from the perturbations may result in deep neural networks wrongly predicting the emotional states. We propose a novel federated adversarial learning framework for protecting both data and deep neural networks. The proposed framework consists of i) federated learning for data privacy, and ii) adversarial training at the training stage and randomisation at the testing stage for model robustness. The experiments show that our proposed framework can effectively protect the speech data locally and improve the model robustness against a series of adversarial attacks.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 32 of its 65 references that are in the map. First posted on arXiv 9 Mar 2022.

Builds on

32 of 65 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  7. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  10. 2016Adversarial Machine Learning at Scalecited by 936
  11. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  12. 2019Towards Federated Learning at Scale: System Designcited by 832
20 more
  1. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
  2. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  3. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  4. 2017Mitigating Adversarial Effects Through Randomizationcited by 383
  5. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  6. 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
  7. 2018Adversarial Robustness Toolbox v1.0.0cited by 215
  8. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  9. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 172
  10. 2019Are Labels Required for Improving Adversarial Robustness?cited by 163
  11. 2017Crafting Adversarial Examples For Speech Paralinguistics Applicationscited by 30
  12. 2019Adversarial Attacks on Spoofing Countermeasures of automatic speaker verificationcited by 23
  13. 2019Speech Emotion Recognition with Dual-Sequence LSTM Architecturecited by 23
  14. 2021EmoNet: A Transfer Learning Framework for Multi-Corpus Speech Emotion Recognitioncited by 17
  15. 2021Failure Prediction in Production Line Based on Federated Learning: An Empirical Studycited by 11
  16. 2020FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applicationscited by 10
  17. 2021Privacy attacks for automatic speech recognition acoustic models in a federated learning frameworkcited by 10
  18. 2018Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustnesscited by 9
  19. 2020CAA-Net: Conditional Atrous CNNs with Attention for Explainable Device-robust Acoustic Scene Classificationcited by 6
  20. 2019Privacy is What We Care About: Experimental Investigation of Federated Learning on Edge Devicescited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 1.

6 papers.

  1. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  2. 2023A Comprehensive Survey on Heart Sound Analysis in the Deep Learning Eracited by 7
  3. 2023Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environmentscited by 2
  4. 2023Pelta: Shielding Transformers to Mitigate Evasion Attacks in Federated Learningcited by 1
  5. 2024STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognitioncited by 1
  6. 2022Developing an AI-enabled IIoT platform -- Lessons learned from early use case validationcited by 0