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 neural networks (DNNs) have gained prominence in various applications,such as classification, recognition, and prediction, prompting increasedscrutiny of their properties. A fundamental attribute of traditional DNNs istheir vulnerability to modifications in input data, which has resulted in theinvestigation of adversarial attacks. These attacks manipulate the data inorder to mislead a DNN. This study aims to challenge the efficacy andgeneralization of contemporary defense mechanisms against adversarial attacks.Specifically, we explore the hypothesis proposed by Ilyas et. al, which positsthat DNN image features can be either robust or non-robust, with adversarialattacks targeting the latter. This hypothesis suggests that training a DNN on adataset consisting solely of robust features should produce a model resistantto adversarial attacks. However, our experiments demonstrate that this is notuniversally true. To gain further insights into our findings, we analyze theimpact of adversarial attack norms on DNN representations, focusing on samplessubjected to $L_2$ and $L_{\infty}$ norm attacks. Further, we employ canonicalcorrelation analysis, visualize the representations, and calculate the meandistance between these representations and various DNN decision boundaries. Ourresults reveal a significant difference between $L_2$ and $L_{\infty}$ norms,which could provide insights into the potential dangers posed by $L_{\infty}$norm attacks, previously underestimated by the research community.

Not So Robust After All: Evaluating the Robustness of Deep Neural Networks to Unseen Adversarial Attacks