Reported 98% accuracy of representation learning for encrypted traffic classification is largely an artifact of per-packet data leakage and unfrozen fine-tuning; under realistic evaluation, deep representations underperform shallow feature-based baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Sweet Danger of Sugar: Debunking Representation Learning for Encrypted Traffic Classification
Reported 98% accuracy of representation learning for encrypted traffic classification is largely an artifact of per-packet data leakage and unfrozen fine-tuning; under realistic evaluation, deep representations underperform shallow feature-based baselines.