PRIME: Plasticity-Robust Incremental Model for Encrypted Traffic Classification in Dynamic Network Environments

TL;DR

PRIME introduces a plasticity-robust incremental learning framework for encrypted traffic classification, effectively maintaining model performance amid evolving network environments and new attack types.

Contribution

The paper proposes the PRIME framework that dynamically adjusts model parameters to address plasticity decline in incremental learning for encrypted traffic classification.

Findings

PRIME outperforms existing incremental learning methods in multiple datasets.

PRIME maintains high classification accuracy with minimal parameter increase.

The framework effectively mitigates plasticity issues in dynamic network environments.

Abstract

With the continuous development of network environments and technologies, ensuring cyber security and governance is increasingly challenging. Network traffic classification(ETC) can analyzes attributes such as application categories and malicious intent, supporting network management services like QoS optimization, intrusion detection, and targeted billing. As the prevalence of traffic encryption increases, deep learning models are relied upon for content-agnostic analysis of packet sequences. However, the emergence of new services and attack variants often leads to incremental tasks for ETC models. To ensure model effectiveness, incremental learning techniques are essential; however, recent studies indicate that neural networks experience declining plasticity as tasks increase. We identified plasticity issues in existing incremental learning methods across diverse traffic samples and proposed the PRIME framework. By observing the effective rank of model parameters and the proportion of inactive neurons, the PRIME architecture can appropriately increase the parameter scale when the model's plasticity deteriorates. Experiments show that in multiple encrypted traffic datasets and different category increment scenarios, the PRIME architecture performs significantly better than other incremental learning algorithms with minimal increase in parameter scale.