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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Information leakage is becoming a critical problem as various informationbecomes publicly available by mistake, and machine learning models train onthat data to provide services. As a result, one's private information couldeasily be memorized by such trained models. Unfortunately, deleting informationis out of the question as the data is already exposed to the Web or third-partyplatforms. Moreover, we cannot necessarily control the labeling process and themodel trainings by other parties either. In this setting, we study the problemof targeted disinformation generation where the goal is to dilute the data andthus make a model safer and more robust against inference attacks on a specifictarget (e.g., a person's profile) by only inserting new data. Our method findsthe closest points to the target in the input space that will be labeled as adifferent class. Since we cannot control the labeling process, we insteadconservatively estimate the labels probabilistically by combining decisionboundaries of multiple classifiers using data programming techniques. Ourexperiments show that a probabilistic decision boundary can be a good proxy forlabelers, and that our approach is effective in defending against inferenceattacks and can scale to large data.

Redactor: A Data-centric and Individualized Defense Against Inference Attacks