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

In recent years, the proliferation of so-called "fake news" has caused muchdisruptions in society and weakened the news ecosystem. Therefore, to mitigatesuch problems, researchers have developed state-of-the-art models toauto-detect fake news on social media using sophisticated data science andmachine learning techniques. In this work, then, we ask "what if adversariesattempt to attack such detection models?" and investigate related issues by (i)proposing a novel threat model against fake news detectors, in whichadversaries can post malicious comments toward news articles to mislead fakenews detectors, and (ii) developing MALCOM, an end-to-end adversarial commentgeneration framework to achieve such an attack. Through a comprehensiveevaluation, we demonstrate that about 94% and 93.5% of the time on averageMALCOM can successfully mislead five of the latest neural detection models toalways output targeted real and fake news labels. Furthermore, MALCOM can alsofool black box fake news detectors to always output real news labels 90% of thetime on average. We also compare our attack model with four baselines acrosstwo real-world datasets, not only on attack performance but also on generatedquality, coherency, transferability, and robustness.

MALCOM: Generating Malicious Comments to Attack Neural Fake News Detection Models