FINDING · EVALUATION

Closed-world evaluation substantially overestimates deployment robustness for darknet traffic classifiers. XGBoost Macro-F1 drops from 88.8% to 46.1% in I2P and Random Forest from 87.4% to 45.7% when unknown services are introduced at inference time under leave-one-service-out evaluation. FreeNet shows the highest closed-world inflation, with RF reaching 96.0% closed-world vs. 61.9% under open-world forced classification.

From 2026-saleem-open-world-darknet-trafficOpen-World Darknet Traffic Recognition Under Leave-One-Service-Out Evaluation · §IV-A, Table II · 2026 · arXiv preprint

Implications

Tags

censors
generic
techniques
ml-classifiertraffic-shape
defenses
tor

Extracted by claude-sonnet-4-6 — review before relying.