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

Recent research has proposed the use of Semi Adversarial Networks (SAN) forimparting privacy to face images. SANs are convolutional autoencoders thatperturb face images such that the perturbed images cannot be reliably used byan attribute classifier (e.g., a gender classifier) but can still be used by aface matcher for matching purposes. However, the generalizability of SANsacross multiple arbitrary gender classifiers has not been demonstrated in theliterature. In this work, we tackle the generalization issue by designing anensemble SAN model that generates a diverse set of perturbed outputs for agiven input face image. This is accomplished by enforcing diversity among theindividual models in the ensemble through the use of different dataaugmentation techniques. The goal is to ensure that at least one of theperturbed output faces will confound an arbitrary, previously unseen genderclassifier. Extensive experiments using different unseen gender classifiers andface matchers are performed to demonstrate the efficacy of the proposedparadigm in imparting gender privacy to face images.

Gender Privacy: An Ensemble of Semi Adversarial Networks for Confounding Arbitrary Gender Classifiers