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

Detecting adversarial examples currently stands as one of the biggestchallenges in the field of deep learning. Adversarial attacks, which produceadversarial examples, increase the prediction likelihood of a target class fora particular data point. During this process, the adversarial example can befurther optimized, even when it has already been wrongly classified with 100%confidence, thus making the adversarial example even more difficult to detect.For this kind of adversarial examples, which we refer to as over-optimizedadversarial examples, we discovered that the logits of the model provide solidclues on whether the data point at hand is adversarial or genuine. In thiscontext, we first discuss the masking effect of the softmax function for theprediction made and explain why the logits of the model are more useful indetecting over-optimized adversarial examples. To identify this type ofadversarial examples in practice, we propose a non-parametric andcomputationally efficient method which relies on interquartile range, with thismethod becoming more effective as the image resolution increases. We supportour observations throughout the paper with detailed experiments for differentdatasets (MNIST, CIFAR-10, and ImageNet) and several architectures.

Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding