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 is a type of machine learning that adapts a deep hierarchy ofconcepts. Deep learning classifiers link the most basic version of concepts atthe input layer to the most abstract version of concepts at the output layer,also known as a class or label. However, once trained over a finite set ofclasses, some deep learning models do not have the power to say that a giveninput does not belong to any of the classes and simply cannot be linked.Correctly invalidating the prediction of unrelated classes is a challengingproblem that has been tackled in many ways in the literature. Novelty detectiongives deep learning the ability to output "do not know" for novel/unseenclasses. Still, no attention has been given to the security aspects of noveltydetection. In this paper, we consider the case study of abstraction-basednovelty detection and show that it is not robust against adversarial samples.Moreover, we show the feasibility of crafting adversarial samples that fool thedeep learning classifier and bypass the novelty detection monitoring at thesame time. In other words, these monitoring boxes are hackable. We demonstratethat novelty detection itself ends up as an attack surface.

Hack The Box: Fooling Deep Learning Abstraction-Based Monitors