IP density (number of IP addresses per person) is the single most predictive feature of a country's Freedom of Press Index. A normalized IP density value of ≥0.167 reliably predicts high freedom of expression, while normalized maximum BGP policy-compliant path length ≥0.643 reliably predicts low freedom.

Domestic mesh traceroutes (both source and destination inside the target country) uncovered 5,562 new AS edges not present in standard BGP table–derived topology datasets, far exceeding the 647 new edges found by inside-out/outside-in traceroutes using up to 25 probes. Russia, the US, France, the UK, and Ukraine gained the most new edges.

§2.2, Table 1 evaluation

A decision tree with linear regression at leaves (DTLR) trained on AS-topology features for 168 countries predicts Freedom House freedom category (Free/Partly Free/Not Free) with 95% accuracy. Average FPI prediction error was 3.47%, and prediction error remained ≤8 points (on a 0–100 scale) 90% of the time under leave-one-out cross-validation.

§3.3 evaluation

Iran's national policy forces all domestic ASes to route through a single national telecom AS (AS 12880), resulting in Iran connecting to only 6 international networks. By contrast, Singapore has 257 domestic ASes connected to 3,022 international ASes despite similar geographic scale.

§1, §5 detection

Singapore's AS topology — 257 domestic ASes with 3,022 international connections — resembles that of high-freedom countries, yet its Freedom of Press Index is 33 (Partly Free), making it a structural outlier where rich international BGP connectivity coexists with enforced information controls. Our DTLR model predicts Singapore's FPI should be ≥70 (Free).

§5 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