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

This paper addresses detection of a reverse engineering (RE) attack targetinga deep neural network (DNN) image classifier; by querying, RE's aim is todiscover the classifier's decision rule. RE can enable test-time evasionattacks, which require knowledge of the classifier. Recently, we proposed aquite effective approach (ADA) to detect test-time evasion attacks. In thispaper, we extend ADA to detect RE attacks (ADA-RE). We demonstrate our methodis successful in detecting "stealthy" RE attacks before they learn enough tolaunch effective test-time evasion attacks.

When Not to Classify: Detection of Reverse Engineering Attacks on DNN Image Classifiers