An SVM classifier using a 60-dimensional feature vector — 10 topological network metrics (assortativity, clustering coefficient, diameter, radius, betweenness centrality, degree distribution exponents) plus 50 Laplacian eigenvalues — can detect network-level censorship without any content analysis. The classifier successfully distinguishes censored from uncensored reply-graphs even at the lowest tested censorship level of γ=0.1 (10% edge removal), using 10-fold cross-validation repeated 10 times.

Cascade-based censorship (ICM model) and uniform random deletion produce measurably different topological signatures: cascade removal causes greater increases in network diameter and radius as the censorship fraction γ increases and a substantial increase in assortativity at mid-removal levels (γ=0.2–0.5), whereas uniform deletion shows slower, more gradual changes across these same metrics.

§4.1 evaluation

Censors on Sina Weibo were documented retroactively removing entire repost cascades started from a single sensitive post. Extrapolating from sampled data, prior work estimated that up to 4,200 workers working eight-hour shifts would be required to match the censorship demand on Sina Weibo alone, with documented peak hours for deletion activity.

§2 Related work evaluation

A random sample of Sina Weibo messages found that 16.25% were deleted overall, with geographic distribution having a strong impact: up to 53% of messages from some Chinese provinces were deleted. Nearly 30% of all deletions occurred within the first 5–30 minutes of posting, and up to 90% within 24 hours of the posting.

§2 Related work evaluation

The paper proposes a black-box methodology for detecting censorship bias in LLMs by comparing responses to identical prompts in Simplified vs. Traditional Chinese — scripts for the same spoken language — controlling for translation quality while exploiting that Simplified Chinese training data is disproportionately sourced from mainland China's censored internet. Each prompt is repeated ten times and scored for similarity to censored text using an XLM-RoBERTa classifier fine-tuned on Baidu Baike (censored) vs. Chinese Wikipedia (uncensored) with scores from 0 to 1.

2024-ahmed-extended §2 / §2.4 keyword-filteringml-classifiermeasurement-platform

Majority-vote ML inference (OCSVM + IF) over OONI data uncovered at least 5 previously undocumented DNS injection IPs active in Russia (e.g., 195.19.90.226, 95.167.13.51, 61.95.167.13.50, 188.19.132.154, 144.85.142.29.248) absent from OONI's existing blocking-fingerprints database, along with novel fingerprints in Italy, Czech Republic, and the UK. Records with fewer than 50 instances were excluded as a conservative false-positive filter.

2024-calle-toward §4.3, Table 5 dns-poisoningml-classifiermeasurement-platform

XGBoost trained on a single month of OONI data achieves near-optimal performance; expanding the training window to 24 months produces deviations of only 0–5 percentage points for FNR, 0.07 PP for FPR, and 0.10 PP for accuracy — suggesting that larger windows introduce noise and overfitting rather than improving detection. Isolation Forest performance degrades more sharply, with accuracy dropping ~5 PP as training data grows beyond 6 months.

2024-calle-toward §4.2, Figure 3 dns-poisoningml-classifiermeasurement-platform

For the Isolation Forest model, resolver ASN (SHAP importance 0.237) and probe ASN (0.220) are the two most predictive features for DNS tampering, reflecting that censorship is topologically concentrated at specific network vantage points. For XGBoost, headers_match dominates (0.317), followed by asn_control_match (0.177), indicating that supervised models rely more on cross-layer consistency signals. DNS tampering represents only 0.5–0.8% of all OONI measurements across 2022–2023 (Figure 2), creating severe class imbalance in any training set.

2024-calle-toward §4.1, Table 4, Figure 2 dns-poisoningml-classifiermeasurement-platform

XGBoost achieves a False Positive Rate of 0.0005, True Positive Rate of 0.9403, and overall accuracy of 0.9991 on OONI global DNS measurement data (2.5% stratified sample), vastly outperforming unsupervised alternatives: Isolation Forest achieves FPR 0.1321 / ACC 0.8699, and One-Class SVM degrades to FPR 0.9711 / ACC 0.0598, making OCSVM effectively unusable for this task.

2024-calle-toward §4.1, Table 3 dns-poisoningml-classifiermeasurement-platform

CenDTect (Tsai et al., NDSS 2024) uses decision trees and a novel clustering method on Censored Planet plus OONI data to identify blocking policies and provide interpretable insights at local and country levels. A separate approach (Duncan & Chen, 2023) applies sequence-to-sequence models and CNN image classification — treating network reachability data as grayscale images — to distinguish censored from uncensored content.

2024-gao-extended §2 Related Works measurement-platformml-classifier