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 deep learning models have shown remarkable performance in imageclassification. While these deep learning systems are getting closer topractical deployment, the common assumption made about data is that it does notcarry any sensitive information. This assumption may not hold for manypractical cases, especially in the domain where an individual's personalinformation is involved, like healthcare and facial recognition systems. Weposit that selectively removing features in this latent space can protect thesensitive information and provide a better privacy-utility trade-off.Consequently, we propose DISCO which learns a dynamic and data driven pruningfilter to selectively obfuscate sensitive information in the feature space. Wepropose diverse attack schemes for sensitive inputs \& attributes anddemonstrate the effectiveness of DISCO against state-of-the-art methods throughquantitative and qualitative evaluation. Finally, we also release an evaluationbenchmark dataset of 1 million sensitive representations to encourage rigorousexploration of novel attack schemes.

DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks