For datagram-mode BiFEP (UDP), a configurable linger depth L prevents permanent one-sided close: without linger (L=0), one-sided ACK loss causes the peer that closed first to go silent at epoch 4, making the missing ACK permanently undeliverable and leaving the remote endpoint live indefinitely (e⋆=⊥). With one-bucket linger (L=1), the closing endpoint continues retransmitting FIN+ACK through the next close bucket, resolving all one-sided ACK-loss scenarios in Table VI within epochs 8–12 across all six tested drop counts.

The Rust BiFEP reference implementation (≈20.4k lines: 2,195 datastream, 989 datagram, 813 shared, 16,375 harness) achieves 28.2 MiB/s goodput at 37.0 µs per epoch operation for datastreams, and 420 MiB/s at 1.36 µs per atomic send/receive for datagrams; all 62,119 conformance assertions passed across 491 trials and 5,321 logical epochs, with 0 forged semantics across 360 datastream and 120 datagram active-integrity trials.

§VII; §VIII-A,B,C; Table II; Table V evaluation

The BiFEP datastream construction uses a 'wrapper' layer with authenticated DATA, DUMMY, and FIN frames over an independently keyed inner FEP per direction, revealing only a public sending schedule ΓX(t) and quantized closing epoch from the set Ecl — the exact private half-close time is hidden behind continued cover traffic. Empirical passive diagnostics on the Rust implementation show byte entropy of 7.999279–7.999749 bits/byte, maximum absolute byte correlation of 0.004668, and a random-forest ROC-AUC of 0.485 (95% CI [0.428, 0.542]) distinguishing DATA from ChaCha20 — not significantly better than chance.

§IV; §VIII-D, Table IV defense

Naïve composition of two unidirectional FEPs leaks private half-close events: when A half-closes after epoch 2 while B's response continues through epoch 6, the zero output in the A→B direction exposes A's private state even though all transmitted bytes appear uniformly random. This attack was confirmed empirically — naive composition leaked in 3/3 close-witness trials versus 0/3 for BiFEP.

§III-D, Proposition 1; Table II (Close-leak witness row) detection

None of the six surveyed deployed protocols — TLS 1.3, QUIC v1, WireGuard, Shadowsocks 2022, obfs4, and Tor — provides the full set of BiFEP security properties (exact shaping, delivery, protocol-state integrity, private half-close, and cross-direction isolation) at the specification level.

§I (abstract contribution bullet); §VIII-G (referenced protocol comparison) evaluation

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

Based on analysis of over 100,000 leaked Geedge Networks documents, InterSecLab (2025) found that Geedge supplied China-GFW-equivalent censorship and surveillance systems to Kazakhstan, Ethiopia, Pakistan, and Myanmar. The systems include deep packet inspection, real-time mobile user monitoring, fine-grained traffic control, regionally customizable censorship rules, and — per WIRED's reporting — ML-based extraction of metadata from encrypted traffic to determine whether a flow is likely from a VPN or circumvention tool.

2026-anon-2026-27-vpn §8 (InterSecLab / WIRED section) dpiml-classifierfully-encrypted-detecttraffic-shape

LetsVPN permanently exited the Chinese mainland market in late April 2026 after its technical team spent 20 days making hourly adjustments and confirmed it could not restore connectivity. The official announcement designated April 8, 2026 as the effective service-termination date and initiated a full refund program.

2026-anon-letsvpn-vpn Official announcement & §Introduction dpitls-fingerprintfully-encrypted-detect

The scheme's core mechanism samples a candidate set of tokens at each generation step and constructs a bijective map from possible message bit strings to those tokens. Selecting the output token via this map provably preserves the original model's sampling distribution, yielding output that is computationally indistinguishable from unmodified model output.

2026-bai-provable-secure-steganography Abstract / core mechanism traffic-shapefully-encrypted-detect

AEGIS, a flow-physics-only ML classifier using a Hyperbolic Liquid State Space Model evaluated on a 400GB adversarial corpus including VLESS Reality, GhostBear, and AMOI-morphed traffic, achieves F1-score 0.9952, 99.50% TPR, and 0.2141% FPR at 262.27 µs inference latency on an RTX 4090. The system discards all payload bytes and classifies traffic exclusively on 6-dimensional flow physics: packet size, inter-arrival time, directionality, TCP window size, TCP flags, and payload ratio.

2026-ferrel-aegis-adversarial-entropy-guided §V, Table III ml-classifiertraffic-shapefully-encrypted-detect

Explicitly disentangling packet headers (structured, low-entropy) from encrypted payloads (high-entropy, stochastic) into separate MoE branches yields consistent gains across six datasets: 86.85% F1 on 120-class TLS 1.3 traffic (CSTNET-TLS), 97.88% F1 on USTC-TFC2016 malware/benign flows, and 92.65% F1 on imbalanced IoT traffic (CIC-IoT2022), demonstrating that headers and payloads carry fundamentally different and independently exploitable discriminative signals.

2026-he-trafficmoe-heterogeneity-aware-mixture §III-A, §IV-B, Tables II–III ml-classifierdpifully-encrypted-detect