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

Even before deep learning architectures became the de facto models forcomplex computer vision tasks, the softmax function was, given its elegantproperties, already used to analyze the predictions of feedforward neuralnetworks. Nowadays, the output of the softmax function is also commonly used toassess the strength of adversarial examples: malicious data points designed tofail machine learning models during the testing phase. However, in this paper,we show that it is possible to generate adversarial examples that takeadvantage of some properties of the softmax function, leading to undesiredoutcomes when interpreting the strength of the adversarial examples at hand.Specifically, we argue that the output of the softmax function is a poorindicator when the strength of an adversarial example is analyzed and that thisindicator can be easily tricked by already existing methods for adversarialexample generation.

How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples