Fine-tuned BERT and RoBERTa steganalysis discriminators achieve only 47.8–50.6% detection accuracy across GPT-2, OPT-1.3B, and Llama-2-7B stegotext — indistinguishable from random guessing. Human evaluators perform similarly poorly (46.6–50.6% accuracy, F1 ≤ 51.5%), while the paper notes statistical classifiers already outperform humans on this discrimination task.

The vanilla range-coding baseline suffers from two provable security failures that RRC corrects: (1) distortion of the token probability distribution because interval boundaries do not align with token probabilities, and (2) randomness reuse across sampling steps, which exposes detectable statistical bias. The rotation mechanism specifically addresses both by introducing fresh PRNG-seeded randomness o~U(0,1) at each step and applying a modulo rotation to the decimal state.

§3.2, §4 defense

Rotation Range-Coding (RRC) steganography achieves approximately 100% entropy utilization (99.98% on GPT-2) while maintaining zero KL divergence at every generative step, outperforming all prior provably-secure baselines: SparSamp at 96.76%, Discop w/ sort at 95.17%, iMEC at 71.44%. The rotation mechanism transforms the discrete uniform random variable into a continuous uniform at each step, preserving the original LM probability distribution exactly.

§5.3, Table 1 defense

RRC steganography achieves an embedding speed of up to 1554.66 bits/s on GPT-2 — the fastest among all provably-secure methods tested — and sustains approximately 1500 bits/s across message lengths from 64 to 1024 bits. Embedding a 128-bit secret message takes 0.082 seconds, and the method scales to at least 8192-bit messages (13.5 seconds, 99.99% entropy utilization) without an upper bound on message length.

§6.4, Table 2 evaluation

RRC steganography is training-free, model-agnostic, and plug-and-play: it requires no modification to the underlying language model and was validated on GPT-2, OPT-1.3B, and Llama-2-7B. The symmetric-key design requires only that sender and receiver agree on a shared PRNG seed and the secret message length l before communication.

§4, §7 defense

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

NATA (Non-invasive Active Traffic-correlation Analysis) injects low-frequency bandwidth waveforms (sinusoidal, square-wave, triangular) into Tor TCP connections at an upstream gateway without endpoint compromise, payload decryption, or Tor-browser modification. BM-Net, a selective state-space classifier trained on the exit-side observations, achieves a 99.65% binary detection F1 score distinguishing watermarked from natural traffic on a 20,000-trace real-world dataset.

2026-fan-activeflowmark-assessing-tor §IV, §VI.D, Table III flow-correlationtraffic-shapeml-classifier

BM-Net achieves a 99.65% binary detection F1 score for distinguishing bandwidth-watermarked Tor flows from natural traffic, outperforming all evaluated baselines (next best: TikTok at 75.96% F1). The accuracy gap stems from active perturbation imposing a deterministic low-frequency throughput constraint rather than relying on subtle natural metadata, making the detection task fundamentally easier than passive website fingerprinting.

2026-fan-activeflowmark-assessing-tor §VI-D, Table III–IV flow-correlationtraffic-shapeml-classifier

BM-Net achieves a 99.65% binary detection F1 score distinguishing watermarked from natural Tor flows, and a 97.5% macro-F1 score for fine-grained modulation classification across sinusoidal, square-wave, and triangular patterns. The fine-grained test set contains 201 held-out samples collected from ten clients across five geographic regions (Europe, North America, Australia, Southeast Asia, East Asia), with training traces including traffic collected under WTF-PAD and Walkie-Talkie defenses.

2026-fan-activeflowmark-assessing-tor §VI-D, Table III, Table V flow-correlationml-classifiertraffic-shape

BM-Net achieves a 97.5% macro-F1 score for fine-grained classification of three modulation geometries (sinusoidal, square-wave, triangular) from noisy exit-side Tor observations using only 201 labeled test samples collected across cross-continental Tor paths. Residual errors concentrate between natural traffic and square-wave modulation, as abrupt low-rate transitions are partially smoothed by Tor multiplexing and network jitter.

2026-fan-activeflowmark-assessing-tor §VI-D, Table V flow-correlationml-classifiertraffic-shape

Fine-grained modulation classification (natural vs. sinusoidal vs. square-wave vs. triangular) achieves 97.5% macro-F1 on a 201-sample held-out test set. Square-wave waveforms are the hardest class (F1 = 95.7%), while sinusoidal and triangular each reach 99.0% F1, because abrupt square-wave transitions are partially smoothed by Tor multiplexing and network dynamics.

2026-fan-activeflowmark-assessing-tor §VI.D.2, Table V flow-correlationtraffic-shapeml-classifier