Decorrelative network architecture for robust electrocardiogram classification

To achieve adequate trust in patient-critical medical tasks, artificial intelligence must be able to recognize instances where they cannot operate confidently. Ensemble methods are deployed to estimate uncertainty, but models in an ensemble often share the same vulnerabilities to adversarial attacks. We propose an ensemble approach based on feature decorrelation and Fourier partitioning for teaching networks diverse features, reducing the chance of perturbation-based fooling. We test our approach against white-box attacks in single- and multi-channel electrocardiogram classification and adapt adversarial training and DVERGE into an ensemble framework for comparison. Our results indicate that the combination of decorrelation and Fourier partitioning maintains performance on unperturbed data while demonstrating superior uncertainty estimation on projected gradient descent and smooth adversarial attacks of various magnitudes. Furthermore, our approach does not require expensive optimization with adversarial samples during training. These methods can be applied to other tasks for more robust models.