Among six ML classifiers evaluated via 5-fold cross-validation across 296 IoT DNS deployment scenarios, Random Forest (RF) consistently achieved the highest accuracy (~0.891), precision (~0.864), recall (~0.813), and F1 score (~0.831). All six classifiers (LR, KNN, SVM, DT, RF, AB) achieved accuracies between 0.826 and 0.891, indicating that DNS-vs-data classification is robust to classifier choice.
From 2026-lenders-secrets-best-not — Secrets Best Not Shared: DNS Privacy Enhancements for the Constrained IoT
· §5
· 2026
· arXiv preprint
Implications
Assume a state-level adversary will deploy Random Forest or equivalent ensembles; obfuscation must reduce accuracy well below 86% to be practically evasive, since even weaker classifiers achieve 83%+ on unobfuscated traffic.
Evaluate circumvention transports against multiple classifier families, not just neural networks — simpler tree-based methods are highly effective on IoT packet header features.