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

The blooming of social media and face recognition (FR) systems has increasedpeople's concern about privacy and security. A new type of adversarial privacycloak (class-universal) can be applied to all the images of regular users, toprevent malicious FR systems from acquiring their identity information. In thiswork, we discover the optimization dilemma in the existing methods -- the localoptima problem in large-batch optimization and the gradient informationelimination problem in small-batch optimization. To solve these problems, wepropose Gradient Accumulation (GA) to aggregate multiple small-batch gradientsinto a one-step iterative gradient to enhance the gradient stability and reducethe usage of quantization operations. Experiments show that our proposed methodachieves high performance on the Privacy-Commons dataset against black-box facerecognition models.

Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulation