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

In this work, we propose a new and general framework to defend againstbackdoor attacks, inspired by the fact that attack triggers usually follow a\textsc{specific} type of attacking pattern, and therefore, poisoned trainingexamples have greater impacts on each other during training. We introduce thenotion of the {\it influence graph}, which consists of nodes and edgesrespectively representative of individual training points and associatedpair-wise influences. The influence between a pair of training pointsrepresents the impact of removing one training point on the prediction ofanother, approximated by the influence function \citep{koh2017understanding}.Malicious training points are extracted by finding the maximum averagesub-graph subject to a particular size. Extensive experiments on computervision and natural language processing tasks demonstrate the effectiveness andgenerality of the proposed framework.

A General Framework for Defending Against Backdoor Attacks via Influence Graph