Striding with factor 4 (early downsampling) produces the largest single-factor degradation in the ablation study: average macro-F1 drops from 0.9909 to 0.9772 and cross-dataset variance increases from 4.77×10⁻⁵ to 4.51×10⁻⁴, with worst-case dataset performance falling to MIN 0.9524. Fine-grained byte order and short-range structure — protocol headers, payload signatures, repeated byte motifs — carry essential discriminative signal that stride-based aggregation destroys.

Early downsampling via striding (stride=4) is the single most damaging ablation, reducing average macro-F1 from 0.9909 to 0.9772 and increasing cross-dataset variance from 4.77×10⁻⁵ to 4.51×10⁻⁴, while the worst-case dataset drops to F1=0.9524 — far larger degradation than any other design choice including Mamba-1 vs Mamba-2.

§V-B, Table IV detection

A burst of just 5 packets truncated to 320 bytes each (1600 bytes total) suffices for macro-F1 ≥0.9824 across all six benchmarks; the classification token reads from the final recurrent state after a 4-layer Mamba-2 stack processing this fixed-length prefix, with no additional flow-level or session-level context required.

§III-A, §V-A detection

Classification from the first 5 packets × 320 bytes (1600-byte burst) achieves near-perfect accuracy across Tor (F1=0.9990), VPN (F1=0.9871), malware (F1=0.9954), and IoT attack traffic (F1=0.9966), with IP addresses masked and only header and initial payload retained. The earliest portion of each packet provides sufficient discriminative information for a classification decision made within the first kilobyte of a flow.

§III-A, §V-A, Table II–III detection

MambaNetBurst classifies Tor traffic (ISCXTor2016) at F1=0.9990 and VPN traffic (ISCXVPN2016) at F1=0.9871 using only the first 5 packets (1600 bytes total) with no pre-training, matching or exceeding pre-trained baselines like ET-BERT (ISCXTor F1=0.9967, ISCXVPN F1=0.9565) and NetMamba (ISCXTor F1=0.9986, ISCXVPN F1=0.9806) at 2.5–2.7M parameters.

§V-A, Table III detection

Mamba-2's constrained scalar-times-identity A-matrix acts as an implicit regularizer for packet-byte sequences: under matched settings it yields higher mean F1 (0.9909 vs 0.9874), better worst-case F1 (0.9824 vs 0.9769), and 48% lower cross-dataset variance (4.77×10⁻⁵ vs 9.21×10⁻⁵) relative to Mamba-1, while delivering 30–60% faster backward passes and 2–4× lower GPU memory usage.

§V-B, §V-C, Table V detection

Mamba-2 (2.5M parameters) is Pareto-optimal on the accuracy-vs-inference-time frontier: it achieves average macro-F1 of 0.9909 with 30-60% faster backward passes than Mamba-1 and 2-3× faster inference than linear Transformers with FlashAttention-2 at medium-to-large batch sizes on a single RTX 3090. Memory usage is 2-4× lower than Transformer-based counterparts, enabling single-GPU operation at sequence length 1600.

§V-C, §V-D, Figure 2 evaluation

Supervised byte-level training without pre-training reduces total compute by an estimated 3–15× in wall-clock training time and 2–4× in training memory footprint compared to pre-trained Transformer baselines (ET-BERT, YaTC, NetMamba), while achieving equivalent or superior classification F1 across six benchmarks spanning encrypted app identification, VPN/Tor, malware, and IoT attack traffic.

§VI-F, §V-A evaluation

Eliminating self-supervised pretraining reduces total wall-clock training time by an estimated 3-15× relative to ET-BERT, YaTC, and NetMamba, while achieving comparable or superior accuracy. Pretraining in representative baselines typically consumes 10-100× more compute than downstream fine-tuning; removing it also eliminates the risk of negative transfer from mismatched pretraining corpora under concept drift.

§VI-F evaluation

MambaNetBurst achieves macro-F1 of 0.9990 on ISCXTor2016 and 0.9871 on ISCXVPN2016 without any pretraining, matching or exceeding heavily pretrained baselines such as ET-BERT (F1=0.9967/0.9565) and YaTC (F1=0.9986/0.9806). High-accuracy Tor and VPN traffic classification is achievable with a compact 2.5M-parameter supervised model requiring no labeled pretraining corpus.

§V-A, Table III detection

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

Adversarial pre-padding — prepending stochastic byte noise to packets — degrades ET-BERT encrypted traffic classification accuracy from >99% to 25.68%, exposing a structural vulnerability in all payload-byte-dependent detection systems. White-box adversarial attacks (Ayaka AH-MSI) additionally achieve evasion rates exceeding 99.5% against standard continuous-time sequence models via Manifold Shattering, where adversaries align malicious temporal distributions with benign baselines.

2026-ferrel-aegis-adversarial-entropy-guided §II, §VI-A dpiml-classifier

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

Under controlled lab conditions, a CNN trained on packet metadata (ports, sizes, TCP sequence numbers) achieved 99.5% accuracy classifying I2P packets with the 'Without payload' variant, versus only 72.5–76.5% using encrypted payload alone. However, when applied to the full recorded dataset, the 'Without payload' model's accuracy for the dominant irrelevant-traffic class dropped to 95.17% while maintaining 100% on target-class packets — but with a high false-positive rate making it forensically unreliable.

2026-rohrer-convolutional-neural-networks-deanonymisation-i2p §V Second Experiment / Table IV–V ml-classifiertraffic-shapedpi

Amnesty International's 102-page investigation identifies a multi-vendor surveillance stack deployed in Pakistan: Chinese DPI (Geedge/MESA-derived), Canadian social-media monitoring (Netsweeper), and Emirati commercial spyware (Pegasus and FinFisher). The system enables deep packet inspection, SNI-based filtering, and traffic-shape classification at national scale, including targeted interception of encrypted messaging apps and VPN traffic.

2025-amnesty-pakistan-shadows §3, §5 dpisni-blockingip-blockingtraffic-shapeml-classifier

The September 2025 leak of ~600 GB from Geedge Networks and the MESA Lab (Institute of Information Engineering, Chinese Academy of Sciences) is the largest known document disclosure from the GFW vendor ecosystem. It establishes a direct lineage: MESA Lab (founded 2012 by Fang Binxing's team, annual contracted revenue >35M RMB by 2016) spun out Geedge Networks in 2018, with MESA alumni filling key engineering roles (e.g. Zheng Chao as CTO). The leak includes ~64 GB of MESA git repositories, ~35 GB of MESA internal documents, ~15 GB of Geedge internal documents, and a ~3 GB Jira export — providing direct access to source code, work logs, and internal communications behind GFW R&D.

2025-geedge-mesa-leak §4 dpiactive-probingml-classifiersni-blockingfully-encrypted-detect