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 recent advances in natural language processing have yielded many excitingdevelopments in text analysis and language understanding models; however, thesemodels can also be used to track people, bringing severe privacy concerns. Inthis work, we investigate what individuals can do to avoid being detected bythose models while using social media platforms. We ground our investigation intwo exposure-risky tasks, stance detection and geotagging. We explore a varietyof simple techniques for modifying text, such as inserting typos in salientwords, paraphrasing, and adding dummy social media posts. Our experiments showthat the performance of BERT-based models fined tuned for stance detectiondecreases significantly due to typos, but it is not affected by paraphrasing.Moreover, we find that typos have minimal impact on state-of-the-art geotaggingmodels due to their increased reliance on social networks; however, we showthat users can deceive those models by interacting with different users,reducing their performance by almost 50%.

Catch Me If You Can: Deceiving Stance Detection and Geotagging Models to Protect Privacy of Individuals on Twitter