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 show how to jointly exploit adversarial perturbation andmodel poisoning vulnerabilities to practically launch a new stealthy attack,dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when:1) a carefully crafted adversarial perturbation is injected into the inputexamples during inference, and 2) a Trojan backdoor is implanted during thetraining process of the model. We leverage adversarial noise in the input spaceto move Trojan-infected examples across the model decision boundary, making itdifficult to detect. The stealthiness behavior of AdvTrojan fools the usersinto accidentally trust the infected model as a robust classifier againstadversarial examples. AdvTrojan can be implemented by only poisoning thetraining data similar to conventional Trojan backdoor attacks. Our thoroughanalysis and extensive experiments on several benchmark datasets show thatAdvTrojan can bypass existing defenses with a success rate close to 100% inmost of our experimental scenarios and can be extended to attack federatedlearning tasks as well.

A Synergetic Attack against Neural Network Classifiers combining Backdoor and Adversarial Examples