Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks
This work addresses the trustworthiness of deep learning models in clinical practices by assessing their robustness to adversarial attacks, but it is incremental as it applies existing methods to a specific domain.
The paper analyzed the vulnerability of two state-of-the-art deep networks for chest X-ray image classification against ten adversarial attack methods, including gradient-based, score-based, and decision-based attacks, and found that modifying pooling operations affected sensitivity to these attacks.
Recently, there have been several successful deep learning approaches for automatically classifying chest X-ray images into different disease categories. However, there is not yet a comprehensive vulnerability analysis of these models against the so-called adversarial perturbations/attacks, which makes deep models more trustful in clinical practices. In this paper, we extensively analyzed the performance of two state-of-the-art classification deep networks on chest X-ray images. These two networks were attacked by three different categories (ten methods in total) of adversarial methods (both white- and black-box), namely gradient-based, score-based, and decision-based attacks. Furthermore, we modified the pooling operations in the two classification networks to measure their sensitivities against different attacks, on the specific task of chest X-ray classification.