NetTTT: Online Self-Adaptation Inference via Test-Time Training for Encrypted Traffic Classification

Encrypted traffic classification (ETC) serves as a pivotal research for network measurement and quality of service (Qos) management. However, most current approaches rely on statically frozen parameters after training, which remain vulnerable to performance degradation under real-world distribution shifts caused by dynamic network conditions, protocol evolution, and adversarial obfuscation techniques. To tackle this issue, we propose NetTTT, an online self-adaptation framework that, for the first time, performs continuous representation refinement directly at inference time without retraining. NetTTT leverages a hierarchical feature encoder (HFE) that constructs structured dual-modal representations from raw traffic sessions, coupled with a pretrained generic representation extractor to powerfully capture transferable contextual features, and incorporates a lightweight test-time adapter (TTA), which performs unsupervised, layerwise parameter optimization during inference to dynamically align traffic representations with test-time traffic distributions, followed by a compact classifier that efficiently maps adapted representations to traffic categories. Experimental results reveal the superiority of NetTTT across diverse ETC tasks and few-shot scenarios with accuracy improvements ranging from 0.08% to 9.34% over the state-of-the-art (SOTA) baselines. By enabling dynamic adaptation without labeled data or full model retraining, NetTTT bridges the gap between static pretrained models and evolving encrypted traffic, highlighting its potential to provide a practical solution for real-world scenarios.