A simple three-hidden-layer MLP trained on only 13 standard browser attributes achieves AUROC above 0.5 for every tested demographic group: gender 0.663–0.679, age 55+ 0.644, Hispanic ethnicity 0.60, Asian race 0.698, Black race 0.677, and high-income bracket 0.617. Because the model used only attributes already collected by mainstream fingerprinting scripts (e.g., FingerprintJS), richer real-world attribute sets would yield substantially higher demographic inference accuracy.

Simulating a shift from a 0% to 100% male dataset sample changes Shannon entropy estimates by more than 10% for User-Agent (downward) and more than 68% for WebGL Renderer (upward), revealing that prior large fingerprinting studies — Panopticlick (83.6–94.2% unique, predominantly reached via tech-oriented channels) and AmIUnique (90% desktop unique) — likely misrepresent real-world risk due to uncontrolled male bias, as confirmed by a directly comparable study showing 76.5% male participants.

§6, Figure 4 evaluation

Approximately 60% of users in the 8,400-participant US dataset had a unique overall browser fingerprint when combining 13 standard attributes, matching FingerprintJS's advertised 60% accuracy. Fingerprinting risk followed strict monotonic trends: uniqueness increased with age (65+ group most at risk) and decreased with income (household income under $25,000 group at greatest risk), while males showed more unique overall fingerprints but females showed higher uniqueness on passive-fingerprintable attributes (User-Agent, Languages).

§4.1, §6.2, §8.2 evaluation

User-Agent and Accept-Language browser attributes are transmitted in HTTP request headers, enabling passive server-side fingerprinting without JavaScript execution or any browser-detectable signal. In the 8,400-user dataset, the Languages attribute placed Hispanic users (who represent only 11% of the sample) among more than 45% of users with 'es-US' as their Languages value, substantially reducing their anonymity set size versus the general population.

§4.1, §6.2 detection

Screen resolution (572 distinct values, 4.5% unique, entropy 5.51), WebGL Unmasked Renderer (654 distinct values, 3.2% unique, entropy 6.833), and User-Agent (434 distinct values, 2.8% unique, entropy 4.613) are simultaneously the most uniquely identifying individual attributes and the strongest demographic predictors by normalized mutual information across all five demographic categories tested (gender, age, income, Hispanic ethnicity, race).

§7.2, Figure 6, Table 1 detection

Russia's Ministry of Digital Development issued guidelines effective April 15, 2026 requiring popular apps to detect and restrict access from VPN-using devices. RKS Global's analysis of 30 popular Russian Android apps found that 22 of 30 implement VPN detection, and 19 of those transmit the detected VPN status to their servers. This represents a shift from network-layer blocking (TSPU) to app-layer enforcement as an additional censorship vector.

2026-rks-russian-apps-vpn-detection §3, §4 tls-fingerprintml-classifier

The RKS Global report documents a two-tier Russian censorship architecture: TSPU network-layer blocking (documented by Xue et al. 2024) at the ISP level, now supplemented by mandated app-layer VPN detection in the 30 most popular Russian Android apps. This layered approach means a circumvention tool that successfully bypasses TSPU at the network layer can still be detected and reported by the app layer, closing the gap that network-only circumvention leaves open.

2026-rks-russian-apps-vpn-detection §2, §7 tls-fingerprintml-classifiermiddlebox-interference

Obfuscated proxy traffic (including Shadowsocks, VMess, VLESS, Trojan, obfs4, and REALITY) can be reliably fingerprinted by detecting encapsulated TLS handshakes — the inner TLS ClientHello that appears inside an outer encrypted tunnel. This fingerprint is protocol-agnostic: any proxy that wraps TLS-bearing application traffic will produce it. The authors deployed a similarity-based classifier within a mid-size ISP serving over one million users and demonstrated detection with minimal collateral damage.

2024-xue-fingerprinting Abstract, §5, §7 dpitls-fingerprintml-classifier

V2Ray clients emitted TLS ClientHello messages with a hardcoded, rarely-seen ciphersuite (fingerprint ID 8c48b95f67260663 on tlsfingerprint.io) that allowed a machine-learning classifier to identify V2Ray TLS traffic with 0.9999 accuracy; the same classifier could not accurately identify the traffic after the fingerprint was changed. The blocking rule based on the unique ciphersuite could be expressed in a single iptables line.

2020-v2ray-weaknesses §Unique TLS ClientHello Fingerprints tls-fingerprintml-classifier

Frolov and Wustrow show that every major TLS-based circumvention tool (Tor Browser, Lantern, OpenVPN, Psiphon, etc.) produces a TLS ClientHello fingerprint that is statistically distinguishable from real Chrome or Firefox: differences include cipher-suite ordering, extension set, extension ordering, ALPN values, and curve preferences. A passive observer with a classifier over ClientHello fields can identify the tool with high precision without decrypting any traffic.

2015-frolov-the-use-of-tls §3–4 tls-fingerprintdpiml-classifier

Stage 1 of the detection pipeline uses a lightweight heuristic: restrict analysis to IP addresses in "VPS-dense ASNs," which censors already target for resource-intensive inspection of fully-encrypted traffic. This pre-filter dramatically reduces the search space before applying the more expensive dual-role behavioral analysis. The evaluation was conducted without Stages 1 and 3 due to dataset limitations, meaning the reported 23% recall and 0.18% FPR are conservative lower bounds on the full pipeline's performance.

2026-almutairi-server §2.1, §2.2, §3.4 fully-encrypted-detectdpiml-classifier