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 (DL) is the most widely used tool in the contemporary field ofcomputer vision. Its ability to accurately solve complex problems is employedin vision research to learn deep neural models for a variety of tasks,including security critical applications. However, it is now known that DL isvulnerable to adversarial attacks that can manipulate its predictions byintroducing visually imperceptible perturbations in images and videos. Sincethe discovery of this phenomenon in 2013~[1], it has attracted significantattention of researchers from multiple sub-fields of machine intelligence. In[2], we reviewed the contributions made by the computer vision community inadversarial attacks on deep learning (and their defenses) until the advent ofyear 2018. Many of those contributions have inspired new directions in thisarea, which has matured significantly since witnessing the first generationmethods. Hence, as a legacy sequel of [2], this literature review focuses onthe advances in this area since 2018. To ensure authenticity, we mainlyconsider peer-reviewed contributions published in the prestigious sources ofcomputer vision and machine learning research. Besides a comprehensiveliterature review, the article also provides concise definitions of technicalterminologies for non-experts in this domain. Finally, this article discusseschallenges and future outlook of this direction based on the literaturereviewed herein and [2].

Advances in adversarial attacks and defenses in computer vision: A survey