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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep Learning methods have recently seen increased adoption in medicalimaging applications. However, elevated vulnerabilities have been explored inrecent Deep Learning solutions, which can hinder future adoption. Particularly,the vulnerability of Vision Transformer (ViT) to adversarial, privacy, andconfidentiality attacks raise serious concerns about their reliability inmedical settings. This work aims to enhance the robustness of self-ensemblingViTs for the tuberculosis chest x-ray classification task. We proposeSelf-Ensembling ViT with defensive Distillation and Adversarial training(SEDA). SEDA utilizes efficient CNN blocks to learn spatial features withvarious levels of abstraction from feature representations extracted fromintermediate ViT blocks, that are largely unaffected by adversarialperturbations. Furthermore, SEDA leverages adversarial training in combinationwith defensive distillation for improved robustness against adversaries.Training using adversarial examples leads to better model generalizability andimproves its ability to handle perturbations. Distillation using softprobabilities introduces uncertainty and variation into the outputprobabilities, making it more difficult for adversarial and privacy attacks.Extensive experiments performed with the proposed architecture and trainingparadigm on publicly available Tuberculosis x-ray dataset shows SOTA efficacyof SEDA compared to SEViT in terms of computational efficiency with 70x timeslighter framework and enhanced robustness of +9%.

SEDA: Self-Ensembling ViT with Defensive Distillation and Adversarial Training for robust Chest X-rays Classification