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

Backdoor attacks pose a new and emerging threat to AI security, where DeepNeural Networks (DNNs) are trained on datasets added to hidden triggerpatterns. Although the poisoned model behaves normally on benign samples, itproduces anomalous results on samples containing the trigger pattern.Nevertheless, most existing backdoor attacks face two significant drawbacks:their trigger patterns are visible and easy to detect by human inspection, andtheir injection process leads to the loss of natural sample features andtrigger patterns, thereby reducing the attack success rate and the modelaccuracy. In this paper, we propose a novel backdoor attack named SATBA thatovercomes these limitations by using spatial attention mechanism and U-typemodel. Our attack leverages spatial attention mechanism to extract datafeatures and generate invisible trigger patterns that are correlated with cleandata. Then it uses U-type model to plant these trigger patterns into theoriginal data without causing noticeable feature loss. We evaluate our attackon three prominent image classification DNNs across three standard datasets anddemonstrate that it achieves high attack success rate and robustness againstbackdoor defenses. Additionally, we also conduct extensive experiments on imagesimilarity to highlight the stealthiness of our attack.

SATBA: An Invisible Backdoor Attack Based On Spatial Attention