Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review

Abstract

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.

arXiv commentNational Science Open, 2022

References in corpus (21)

• EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces
• Deep learning with convolutional neural networks for EEG decoding and visualization
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
• Is feature selection secure against training data poisoning?
• Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
• Adversarial Feature Selection against Evasion Attacks
• Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
• Brain Computer Interface Technologies in the Coming Decades
• Driver Drowsiness Estimation from EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR)
• Transfer Learning for Motor Imagery Based Brain-Computer Interfaces: A Complete Pipeline
• Adversarial Attacks Against Medical Deep Learning Systems
• Deep Neural Network Ensembles for Time Series Classification
• Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization
• Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
• Security in Brain-Computer Interfaces: State-of-the-art, opportunities, and future challenges
• Privacy-Preserving Brain-Computer Interfaces: A Systematic Review
• Backdoor Attacks against Transfer Learning with Pre-trained Deep Learning Models
• DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples
• Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellers

Cited by in corpus (5)

• Privacy-Preserving Brain-Computer Interfaces: A Systematic Review
• Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs
• Adversarial Filtering Based Evasion and Backdoor Attacks to EEG-Based Brain-Computer Interfaces
• Revisiting Euclidean Alignment for Transfer Learning in EEG-Based Brain-Computer Interfaces
• Adversarial Artifact Detection in EEG-Based Brain-Computer Interfaces