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 techniques have achieved superior performance in computer-aidedmedical image analysis, yet they are still vulnerable to imperceptibleadversarial attacks, resulting in potential misdiagnosis in clinical practice.Oppositely, recent years have also witnessed remarkable progress in defenseagainst these tailored adversarial examples in deep medical diagnosis systems.In this exposition, we present a comprehensive survey on recent advances inadversarial attack and defense for medical image analysis with a novel taxonomyin terms of the application scenario. We also provide a unified theoreticalframework for different types of adversarial attack and defense methods formedical image analysis. For a fair comparison, we establish a new benchmark foradversarially robust medical diagnosis models obtained by adversarial trainingunder various scenarios. To the best of our knowledge, this is the first surveypaper that provides a thorough evaluation of adversarially robust medicaldiagnosis models. By analyzing qualitative and quantitative results, weconclude this survey with a detailed discussion of current challenges foradversarial attack and defense in medical image analysis systems to shed lighton future research directions.

Adversarial Attack and Defense for Medical Image Analysis: Methods and Applications