mlsanityData to 7 Oct 2026

Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review

arXiv 2102.02729 ↗First posted 4 Feb 2021cs.LG cs.CY cs.HCcited by 7

Not on the map. Why?

Abstract (arXiv)

Physiological computing uses human physiological data as system inputs in real time. It includes, or significantly overlaps with, brain-computer interfaces, affective computing, adaptive automation, health informatics, and physiological signal based biometrics. Physiological computing increases the communication bandwidth from the user to the computer, but is also subject to various types of adversarial attacks, in which the attacker deliberately manipulates the training and/or test examples to hijack the machine learning algorithm output, leading to possible user confusion, frustration, injury, or even death. However, the vulnerability of physiological computing systems has not been paid enough attention to, and there does not exist a comprehensive review on adversarial attacks to them. This paper fills this gap, by providing a systematic review on the main research areas of physiological computing, different types of adversarial attacks and their applications to physiological computing, and the corresponding defense strategies. We hope this review will attract more research interests on the vulnerability of physiological computing systems, and more importantly, defense strategies to make them more secure.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 42 of its 130 references that are in the map. First posted on arXiv 4 Feb 2021.

Builds on

42 of 130 references.

References · 42

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2016Adversarial examples in the physical worldcited by 1,762
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  6. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  7. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  8. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  9. 2019Adversarial Training for Free!cited by 638
  10. 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 616
  11. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  12. 2017Adversarial Patchcited by 514
30 more
  1. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  2. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  3. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  4. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  5. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  6. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  7. 2018Is feature selection secure against training data poisoning?cited by 88
  8. 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 86
  9. 2020Secure and Robust Machine Learning for Healthcare: A Surveycited by 77
  10. 2018Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approachcited by 76
  11. 2018Adversarial Attacks Against Medical Deep Learning Systemscited by 61
  12. 2020Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progress Made Since 2016cited by 56
  13. 2019Adversarial Attacks on Deep Neural Networks for Time Series Classificationcited by 53
  14. 2020Backdoor Attacks against Transfer Learning with Pre-trained Deep Learning Modelscited by 43
  15. 2019Adversarial Attacks on Time Seriescited by 40
  16. 2020Transfer Learning for Motor Imagery Based Brain-Computer Interfaces: A Complete Pipelinecited by 31
  17. 2017DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samplescited by 22
  18. 2017Blocking Transferability of Adversarial Examples in Black-Box Learning Systemscited by 19
  19. 2019On the Vulnerability of CNN Classifiers in EEG-Based BCIscited by 17
  20. 2020Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellerscited by 14
  21. 2017Evaluation of PPG Biometrics for Authentication in different statescited by 13
  22. 2019White-Box Target Attack for EEG-Based BCI Regression Problemscited by 13
  23. 2019Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIscited by 13
  24. 2020Adversarial Feature Selection against Evasion Attackscited by 13
  25. 2020Adversarial Attacks to Machine Learning-Based Smart Healthcare Systemscited by 12
  26. 2020EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attackscited by 12
  27. 2017Driver Drowsiness Estimation from EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR)cited by 9
  28. 2017Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularizationcited by 4
  29. 2019Active Learning for Black-Box Adversarial Attacks in EEG-Based Brain-Computer Interfacescited by 3
  30. 2020Cyberattacks on Miniature Brain Implants to Disrupt Spontaneous Neural Signalingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 0; 2024: 3; 2025: 1; 2026: 1.

7 papers.

  1. 2021Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Surveycited by 11
  2. 2025Revisiting Euclidean Alignment for Transfer Learning in EEG-Based Brain-Computer Interfacescited by 7
  3. 2024Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIscited by 5
  4. 2022Adversarial Artifact Detection in EEG-Based Brain-Computer Interfacescited by 4
  5. 2024PAT: Privacy-Preserving Adversarial Transfer for Accurate, Robust and Privacy-Preserving EEG Decodingcited by 2
  6. 2024Adversarial Filtering Based Evasion and Backdoor Attacks to EEG-Based Brain-Computer Interfacescited by 1
  7. 2026SW-ProxyCE: Zero-Query Adversarial Transfer from Public EEG Encoders to Private Downstream Modelscited by 0