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

Automated fact-checking is a needed technology to curtail the spread ofonline misinformation. One current framework for such solutions proposes toverify claims by retrieving supporting or refuting evidence from relatedtextual sources. However, the realistic use cases for fact-checkers willrequire verifying claims against evidence sources that could be affected by thesame misinformation. Furthermore, the development of modern NLP tools that canproduce coherent, fabricated content would allow malicious actors tosystematically generate adversarial disinformation for fact-checkers.  In this work, we explore the sensitivity of automated fact-checkers tosynthetic adversarial evidence in two simulated settings: AdversarialAddition,where we fabricate documents and add them to the evidence repository availableto the fact-checking system, and AdversarialModification, where existingevidence source documents in the repository are automatically altered. Ourstudy across multiple models on three benchmarks demonstrates that thesesystems suffer significant performance drops against these attacks. Finally, wediscuss the growing threat of modern NLG systems as generators ofdisinformation in the context of the challenges they pose to automatedfact-checkers.

Synthetic Disinformation Attacks on Automated Fact Verification Systems