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

Neural network-based image classifiers are powerful tools for computer visiontasks, but they inadvertently reveal sensitive attribute information abouttheir classes, raising concerns about their privacy. To investigate thisprivacy leakage, we introduce the first Class Attribute Inference Attack(CAIA), which leverages recent advances in text-to-image synthesis to infersensitive attributes of individual classes in a black-box setting, whileremaining competitive with related white-box attacks. Our extensive experimentsin the face recognition domain show that CAIA can accurately infer undisclosedsensitive attributes, such as an individual's hair color, gender, and racialappearance, which are not part of the training labels. Interestingly, wedemonstrate that adversarial robust models are even more vulnerable to suchprivacy leakage than standard models, indicating that a trade-off betweenrobustness and privacy exists.

Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations