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.

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.

§4.3, Table 5 detection

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.

§4.2, Figure 3 evaluation

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.

§4.1, Table 3 evaluation

Brown et al. (2023) combined supervised ML models trained on expert-labeled data with unsupervised models establishing a baseline of 'normal' behavior to detect DNS-based censorship from Satellite and OONI datasets, achieving high true-positive rates for both known and new DNS censorship instances. The hybrid supervised/unsupervised approach is proposed as a template for the LLM-based system.

2024-gao-extended §2 Related Works dns-poisoningmeasurement-platformml-classifier

By mapping ML-predicted censored probes back to their DNS response IPs, the authors discovered 748 forged IP addresses used by China's GFW as DNS blocking signatures that OONI's heuristics missed; supervised and unsupervised models also identified several ISP-specific injected IPs absent from even GFWatch's comprehensive signature list, demonstrating that static signature lists substantially undercount active GFW DNS censorship.

2023-brown-augmenting §4.2, Table 4 dns-poisoningml-classifiermeasurement-platform

XGBoost supervised models trained on DNS probe features achieve TPRs of 100% (Satellite) and 99.8% (OONI) at FPRs of 0.0% and 0.2% respectively when using platform-native anomaly labels; cross-source training with GFWatch labels applied to the same records yields 99.4% TPR for Satellite and 86.7% TPR for OONI, with SHAP analysis confirming that ASN and organization name of the returned DNS response IPs are the dominant predictive signal.

2023-brown-augmenting §4.1, Table 2 dns-poisoningml-classifiermeasurement-platform

Of 6,915,266 domains extracted from the 572 GiB Geedge Networks Leak (GNL), 298,955 censored domains (93.7% of all GNL-censored domains) appear in neither Tranco top-1M nor CitizenLab test lists. Measurements across China (Guangzhou/Nanjing), Myanmar, Pakistan, and Algeria confirmed censorship via DNS injection and SNI-based TLS connection termination. The GNL covers 25–62% of Tranco-censored domains across countries, showing substantial but incomplete overlap. This vendor-side ground truth reveals a censorship surface roughly two orders of magnitude larger than curated academic test lists.

2026-sheffey-geedge §4.1, Table 2 dpisni-blockingdns-poisoningmeasurement-platform

Internal Geedge documents confirm active contracts to deploy GFW-derived censorship and surveillance infrastructure in Myanmar, Pakistan, Ethiopia, Kazakhstan, and at least one additional unidentified country under the Belt and Road framework, in addition to domestic deployments in Xinjiang, Jiangsu, and Fujian. The exported product (the Tiangou Secure Gateway / TSG line) is not a stripped-down export variant — leaked TSG documentation shows DPI, active-probing, ML classifiers, and granular per-region traffic control rules that mirror the domestic GFW capability set.

2025-geedge-mesa-leak §5, §6 dpiactive-probingml-classifiersni-blockingdns-poisoningfully-encrypted-detecttraffic-shape

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