On the Vulnerability of CNN Classifiers in EEG-Based BCIs
arXiv:1904.01002
Abstract
Deep learning has been successfully used in numerous applications because of its outstanding performance and the ability to avoid manual feature engineering. One such application is electroencephalogram (EEG) based brain-computer interface (BCI), where multiple convolutional neural network (CNN) models have been proposed for EEG classification. However, it has been found that deep learning models can be easily fooled with adversarial examples, which are normal examples with small deliberate perturbations. This paper proposes an unsupervised fast gradient sign method (UFGSM) to attack three popular CNN classifiers in BCIs, and demonstrates its effectiveness. We also verify the transferability of adversarial examples in BCIs, which means we can perform attacks even without knowing the architecture and parameters of the target models, or the datasets they were trained on. To our knowledge, this is the first study on the vulnerability of CNN classifiers in EEG-based BCIs, and hopefully will trigger more attention on the security of BCI systems.
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Deep learning with convolutional neural networks for EEG decoding and visualization
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Delving into Transferable Adversarial Examples and Black-box Attacks
- The Space of Transferable Adversarial Examples
- Driver Drowsiness Estimation from EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR)
- Understanding and Enhancing the Transferability of Adversarial Examples
- Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization