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

Due to the prosperity of Artificial Intelligence (AI) techniques, more andmore backdoors are designed by adversaries to attack Deep Neural Networks(DNNs).Although the state-of-the-art method Neural Attention Distillation (NAD)can effectively erase backdoor triggers from DNNs, it still suffers fromnon-negligible Attack Success Rate (ASR) together with lowered classificationACCuracy (ACC), since NAD focuses on backdoor defense using attention features(i.e., attention maps) of the same order. In this paper, we introduce a novelbackdoor defense framework named Attention Relation Graph Distillation (ARGD),which fully explores the correlation among attention features with differentorders using our proposed Attention Relation Graphs (ARGs). Based on thealignment of ARGs between both teacher and student models during knowledgedistillation, ARGD can eradicate more backdoor triggers than NAD. Comprehensiveexperimental results show that, against six latest backdoor attacks, ARGDoutperforms NAD by up to 94.85% reduction in ASR, while ACC can be improved byup to 3.23%.

Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation