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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Adversarial attacks on machine learning models have seen increasing interestin the past years. By making only subtle changes to the input of aconvolutional neural network, the output of the network can be swayed to outputa completely different result. The first attacks did this by changing pixelvalues of an input image slightly to fool a classifier to output the wrongclass. Other approaches have tried to learn "patches" that can be applied to anobject to fool detectors and classifiers. Some of these approaches have alsoshown that these attacks are feasible in the real-world, i.e. by modifying anobject and filming it with a video camera. However, all of these approachestarget classes that contain almost no intra-class variety (e.g. stop signs).The known structure of the object is then used to generate an adversarial patchon top of it.  In this paper, we present an approach to generate adversarial patches totargets with lots of intra-class variety, namely persons. The goal is togenerate a patch that is able successfully hide a person from a persondetector. An attack that could for instance be used maliciously to circumventsurveillance systems, intruders can sneak around undetected by holding a smallcardboard plate in front of their body aimed towards the surveillance camera.  From our results we can see that our system is able significantly lower theaccuracy of a person detector. Our approach also functions well in real-lifescenarios where the patch is filmed by a camera. To the best of our knowledgewe are the first to attempt this kind of attack on targets with a high level ofintra-class variety like persons.

Fooling automated surveillance cameras: adversarial patches to attack person detection