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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

A recent source of concern for the security of neural networks is theemergence of clean-label dataset poisoning attacks, wherein correctly labeledpoison samples are injected into the training dataset. While these poisonsamples look legitimate to the human observer, they contain maliciouscharacteristics that trigger a targeted misclassification during inference. Wepropose a scalable and transferable clean-label poisoning attack againsttransfer learning, which creates poison images with their center close to thetarget image in the feature space. Our attack, Bullseye Polytope, improves theattack success rate of the current state-of-the-art by 26.75% in end-to-endtransfer learning, while increasing attack speed by a factor of 12. We furtherextend Bullseye Polytope to a more practical attack model by including multipleimages of the same object (e.g., from different angles) when crafting thepoison samples. We demonstrate that this extension improves attacktransferability by over 16% to unseen images (of the same object) without usingextra poison samples.

Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability