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

Black-Box attacks on machine learning models occur when an attacker, despitehaving no access to the inner workings of a model, can successfully craft anattack by means of model theft. The attacker will train an own substitute modelthat mimics the model to be attacked. The substitute can then be used to designattacks against the original model, for example by means of adversarialsamples. We put ourselves in the shoes of the defender and present a methodthat can successfully avoid model theft by mounting a counter-attack.Specifically, to any incoming query, we slightly perturb our output labeldistribution in a way that makes substitute training infeasible. We demonstratethat the perturbation does not affect the ordinary use of our model, butresults in an effective defense against attacks based on model theft.

The best defense is a good offense: Countering black box attacks by predicting slightly wrong labels