Vulnerability Analysis of Chest X-Ray Image Classification Against\n Adversarial Attacks

2018/07/08 by Saeid Asgari Taghanaki, Taghanaki, Saeid Asgari, Arkadeep Das +3
Biochemistry, Genetics and Molecular Biology · Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Autopsy Techniques and Outcomes #Bacillus and Francisella bacterial research #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.1807.02905

openalex publication_date 2018/07/08 · openalex created_date 2022/08/04 · openalex updated_date 2026/07/28

Abstract

Recently, there have been several successful deep learning approaches for\nautomatically classifying chest X-ray images into different disease categories.\nHowever, there is not yet a comprehensive vulnerability analysis of these\nmodels against the so-called adversarial perturbations/attacks, which makes\ndeep models more trustful in clinical practices. In this paper, we extensively\nanalyzed the performance of two state-of-the-art classification deep networks\non chest X-ray images. These two networks were attacked by three different\ncategories (ten methods in total) of adversarial methods (both white- and\nblack-box), namely gradient-based, score-based, and decision-based attacks.\nFurthermore, we modified the pooling operations in the two classification\nnetworks to measure their sensitivities against different attacks, on the\nspecific task of chest X-ray classification.\n

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning to recognize Abnormalities in Chest X-Rays with Location-Aware\n Dense Networks
• Adversarial Attacks Against Medical Deep Learning Systems
• Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

Related

• On Evaluating Adversarial Robustness of Chest X-ray Classification: Pitfalls and Best Practices
• A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays
• Chest Disease Detection In X-Ray Images Using Deep Learning Classification Method
• Enhancing Deep Learning Chest Disease Diagnosis through Adversarial Training for Robust and Reliable Medical Imaging
• Adversarial Heart Attack: Neural Networks Fooled to Segment Heart\n Symbols in Chest X-Ray Images