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

Backdoor data poisoning is an emerging form of adversarial attack usuallyagainst deep neural network image classifiers. The attacker poisons thetraining set with a relatively small set of images from one (or several) sourceclass(es), embedded with a backdoor pattern and labeled to a target class. Fora successful attack, during operation, the trained classifier will: 1)misclassify a test image from the source class(es) to the target class wheneverthe same backdoor pattern is present; 2) maintain a high classificationaccuracy for backdoor-free test images. In this paper, we make a break-throughin defending backdoor attacks with imperceptible backdoor patterns (e.g.watermarks) before/during the training phase. This is a challenging problembecause it is a priori unknown which subset (if any) of the training set hasbeen poisoned. We propose an optimization-based reverse-engineering defense,that jointly: 1) detects whether the training set is poisoned; 2) if so,identifies the target class and the training images with the backdoor patternembedded; and 3) additionally, reversely engineers an estimate of the backdoorpattern used by the attacker. In benchmark experiments on CIFAR-10, for a largevariety of attacks, our defense achieves a new state-of-the-art by reducing theattack success rate to no more than 4.9% after removing detected suspicioustraining images.

Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing