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

The proliferation of global censorship has led to the development of aplethora of measurement platforms to monitor and expose it. Censorship of thedomain name system (DNS) is a key mechanism used across different countries. Itis currently detected by applying heuristics to samples of DNS queries andresponses (probes) for specific destinations. These heuristics, however, areboth platform-specific and have been found to be brittle when censors changetheir blocking behavior, necessitating a more reliable automated process fordetecting censorship.  In this paper, we explore how machine learning (ML) models can (1) helpstreamline the detection process, (2) improve the potential of usinglarge-scale datasets for censorship detection, and (3) discover new censorshipinstances and blocking signatures missed by existing heuristic methods. Ourstudy shows that supervised models, trained using expert-derived labels oninstances of known anomalies and possible censorship, can learn the detectionheuristics employed by different measurement platforms. More crucially, we findthat unsupervised models, trained solely on uncensored instances, can identifynew instances and variations of censorship missed by existing heuristics.Moreover, both methods demonstrate the capability to uncover a substantialnumber of new DNS blocking signatures, i.e., injected fake IP addressesoverlooked by existing heuristics. These results are underpinned by animportant methodological finding: comparing the outputs of models trained usingthe same probes but with labels arising from independent processes allows us tomore reliably detect cases of censorship in the absence of ground-truth labelsof censorship.

Augmenting Rule-based DNS Censorship Detection at Scale with Machine Learning