Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks

Abstract

Under the epidemic of the novel coronavirus disease 2019 (COVID-19), chest X-ray computed tomography imaging is being used for effectively screening COVID-19 patients. The development of computer-aided systems based on deep neural networks (DNNs) has been advanced, to rapidly and accurately detect COVID-19 cases, because the need for expert radiologists, who are limited in number, forms a bottleneck for the screening. However, so far, the vulnerability of DNN-based systems has been poorly evaluated, although DNNs are vulnerable to a single perturbation, called universal adversarial perturbation (UAP), which can induce DNN failure in most classification tasks. Thus, we focus on representative DNN models for detecting COVID-19 cases from chest X-ray images and evaluate their vulnerability to UAPs generated using simple iterative algorithms. We consider nontargeted UAPs, which cause a task failure resulting in an input being assigned an incorrect label, and targeted UAPs, which cause the DNN to classify an input into a specific class. The results demonstrate that the models are vulnerable to nontargeted and targeted UAPs, even in case of small UAPs. In particular, 2% norm of the UPAs to the average norm of an image in the image dataset achieves >85% and >90% success rates for the nontargeted and targeted attacks, respectively. Due to the nontargeted UAPs, the DNN models judge most chest X-ray images as COVID-19 cases. The targeted UAPs make the DNN models classify most chest X-ray images into a given target class. The results indicate that careful consideration is required in practical applications of DNNs to COVID-19 diagnosis; in particular, they emphasize the need for strategies to address security concerns. As an example, we show that iterative fine-tuning of the DNN models using UAPs improves the robustness of the DNN models against UAPs.

17 pages, 5 figures, 3 tables

References in corpus (17)

• A Survey on Deep Learning in Medical Image Analysis
• Explaining and Harnessing Adversarial Examples
• CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images
• COVID-19 Image Data Collection
• COVID-CT-Dataset: A CT Scan Dataset about COVID-19
• A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2
• COVID-ResNet: A Deep Learning Framework for Screening of COVID19 from Radiographs
• Unveiling COVID-19 from Chest X-ray with deep learning: a hurdles race with small data
• Simple Black-box Adversarial Attacks
• POBA-GA: Perturbation Optimized Black-Box Adversarial Attacks via Genetic Algorithm
• A New Defense Against Adversarial Images: Turning a Weakness into a Strength
• First-order Adversarial Vulnerability of Neural Networks and Input Dimension
• Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networks
• A cascade network for Detecting COVID-19 using chest x-rays
• Simple iterative method for generating targeted universal adversarial perturbations
• Improved Network Robustness with Adversary Critic
• PuVAE: A Variational Autoencoder to Purify Adversarial Examples

Cited by in corpus (4)

• Automated Detection and Forecasting of COVID-19 using Deep Learning Techniques: A Review
• Fuzzy Unique Image Transformation: Defense Against Adversarial Attacks On Deep COVID-19 Models
• The Effects of Image Distribution and Task on Adversarial Robustness
• Adversarial control of synchronization in complex oscillator networks