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

Dataset distillation offers a potential means to enhance data efficiency indeep learning. Recent studies have shown its ability to counteract backdoorrisks present in original training samples. In this study, we delve into thetheoretical aspects of backdoor attacks and dataset distillation based onkernel methods. We introduce two new theory-driven trigger pattern generationmethods specialized for dataset distillation. Following a comprehensive set ofanalyses and experiments, we show that our optimization-based trigger designframework informs effective backdoor attacks on dataset distillation. Notably,datasets poisoned by our designed trigger prove resilient against conventionalbackdoor attack detection and mitigation methods. Our empirical resultsvalidate that the triggers developed using our approaches are proficient atexecuting resilient backdoor attacks.

Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective