English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Under the epidemic of the novel coronavirus disease 2019 (COVID-19), chestX-ray computed tomography imaging is being used for effectively screeningCOVID-19 patients. The development of computer-aided systems based on deepneural networks (DNNs) has been advanced, to rapidly and accurately detectCOVID-19 cases, because the need for expert radiologists, who are limited innumber, forms a bottleneck for the screening. However, so far, thevulnerability of DNN-based systems has been poorly evaluated, although DNNs arevulnerable to a single perturbation, called universal adversarial perturbation(UAP), which can induce DNN failure in most classification tasks. Thus, wefocus on representative DNN models for detecting COVID-19 cases from chestX-ray images and evaluate their vulnerability to UAPs generated using simpleiterative algorithms. We consider nontargeted UAPs, which cause a task failureresulting in an input being assigned an incorrect label, and targeted UAPs,which cause the DNN to classify an input into a specific class. The resultsdemonstrate 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 averagenorm of an image in the image dataset achieves >85% and >90% success rates forthe nontargeted and targeted attacks, respectively. Due to the nontargetedUAPs, the DNN models judge most chest X-ray images as COVID-19 cases. Thetargeted UAPs make the DNN models classify most chest X-ray images into a giventarget class. The results indicate that careful consideration is required inpractical applications of DNNs to COVID-19 diagnosis; in particular, theyemphasize the need for strategies to address security concerns. As an example,we show that iterative fine-tuning of the DNN models using UAPs improves therobustness of the DNN models against UAPs.

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