After crowdsourced (MTurk) enhancement, 88% of stegotexts on average pass a One-Class SVM trained on 150K sentences from Wikipedia, Brown, and Reuters corpora as natural language; pre-enhancement, only 25–58% pass. For calibration, the same classifier correctly rejects 97% of randomly generated sentences as non-natural-language.

Matryoshka achieves an average covert rate of ~3 bits/word after human enhancement; for a 5-word hidden message averaging 5.5 characters per word, the final enhanced stegotext is approximately 73 words. This is roughly 10× the covert rate of Spammimic (~0.3 bits/word), the prior leading approach.

§5 evaluation

A mixed Huffman codebook combining character-level coding with explicit entries for the 300 most frequent English words (covering ~65% of written material) achieves a 52% compression ratio on average across 4,825 sentences of 4–15 words—7 percentage points better than a character-only alphabet—directly increasing the covert bits available per output word.

§3.1 defense

Users required 4.0–5.8 minutes on average to enhance a stegotext into natural language across three experiments, inserting 4–8 extra words per sentence; this is comparable to the time required to write a short email. The random-word-selection baseline consistently required more time and inserted more words, confirming that n-gram-guided word choice meaningfully reduces human editing burden.

§5 evaluation

The Viterbi-based probabilistic decoder achieves zero character error rate on 96%, 93%, and 95% of decoded messages across the three corpora experiments (dreams, animals, facebook). For the small fraction of failures, only 15% of characters on average were corrupted rather than total message loss.

§5 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

The host-profiling censor (passive traffic analysis: count connections per server, block those exceeding a threshold τ within a window w) blocks essentially all circumvention user traffic within 30 time steps for all classifier qualities tested (ρ_TP ∈ {0.9, 0.95, 0.99}), while causing far less collateral damage than zig-zag (never exceeding ~30% innocent server blocking). Snowflake resists this attack well: with w=3, τ=3, over 94.48% of users receive a proxy within 2 steps even with worst-classifier rules, and final unblocked server rates are 91.24–99.04%. The host profiling approach is feasible for passive censors who cannot enumerate the distribution channel.

2026-fares-game §5.2, Table 2, Table 3 traffic-shapeml-classifier

Balboa's synchronous leaf-content replacement adds non-negligible timing differences that allow censors to identify its activity with up to ~90% accuracy over different network conditions. The timing anomaly arises because Balboa performs data substitution directly at each data exchange, delaying the server's response while covert data is prepared.

2026-kamali-huma §I (Introduction), §II-A traffic-shapeml-classifier

Without chunk-based padding, an XGBoost classifier identifies the target website from covert data-chunk sizes with 91% accuracy (Tranco top-100). Chunking at 2 MB reduces accuracy to 12% at a 21.3% bandwidth overhead, while 16 MB chunks reduce accuracy to near random guessing at a 480.3% overhead. Chunks as small as 64 KB already reduce accuracy to 64%, demonstrating a monotonic fingerprinting–overhead tradeoff.

2026-kamali-huma §V-C, Figure 4 website-fingerprintml-classifier

Huma's deferred-reply / double-request receive (DRR) protocol reduces a traffic-fingerprinting XGBoost classifier's accuracy to at most 54% (near random guessing) across geographically distributed clients (San Francisco, Frankfurt, Bangalore). A Kolmogorov-Smirnov test on absolute page-load timing distributions yields D=0.03, p=0.98 for U.S. clients — substantially tighter than Waterfall of Liberty's D=0.11 at p=0.5 — confirming that Huma flows are statistically indistinguishable from benign HTTPS fetches.

2026-kamali-huma §V-D, Table II traffic-shapeml-classifier

When the researchers attempted to use Gemini 2.5 Flash as a third independent LLM judge via its API for evaluating moderation decisions, Gemini automatically blocked all judging attempts citing safety reasons. This occurred even though the research task (judging whether a response is more or less moderated) does not itself produce harmful content. The incident illustrates that LLM safety systems can over-block legitimate research use cases, and that different LLM providers have different thresholds— Claude Haiku 4.5 and GPT-4o completed all judging tasks without safety refusals.

2026-lipphardt-dual §3.3.3 ml-classifierkeyword-filtering