Open set encrypted traffic classification method and system based on structured fine-tuning pre-trained model

By preprocessing and fine-tuning the pre-trained model of encrypted traffic data in a structured manner, the problems of insufficient utilization of protocol structure semantics and lack of sequential modeling in existing technologies are solved. This enables efficient identification and classification of unknown traffic categories, improving the adaptability of the network environment and the effectiveness of security monitoring.

CN122241335APending Publication Date: 2026-06-19BEIJING UNIV OF POSTS & TELECOMM
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING UNIV OF POSTS & TELECOMM
Filing Date
2026-01-29
Publication Date
2026-06-19

AI Technical Summary

⚠Technical Problem

Existing encrypted traffic classification methods based on pre-trained models do not fully utilize protocol structure semantics, lack structured modeling of traffic sequence, and have insufficient discriminative power in feature space in open set scenarios, making it difficult to effectively identify unknown traffic categories.

⚗Method used

By preprocessing encrypted network traffic data into a sequence of terms, and using a pre-trained language model for structured fine-tuning, including header field rearrangement and flow packet segmentation, aggregated feature vectors are extracted and identified using an open set classification algorithm based on distance metrics.

🎯Benefits of technology

It improves the model's recognition capabilities in open set scenarios, enabling it to efficiently and reliably identify unknown traffic categories, thereby enhancing the network environment's adaptability and security monitoring effectiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

This invention provides an open-set encrypted traffic classification method and system based on a structured fine-tuning pre-trained model, comprising: preprocessing the original encrypted traffic into a lexical sequence that can be processed by a language model; fine-tuning the pre-trained language model using the lexical sequence: performing structured guidance operations on the lexical sequence such as header field rearrangement and / or flow packet segmentation and representation to guide the model to learn the structured semantics of the traffic; extracting aggregated feature vectors of the traffic sequence to be classified using the fine-tuned model; and based on the feature vectors, using an open-set classification algorithm based on distance metrics to determine whether it belongs to an unknown category, and if not, further determining its specific known category. This invention can guide the model to deeply understand the protocol and packet sequence structure of encrypted traffic, thereby achieving both high-precision classification of known traffic and effective identification of unknown traffic in open-set scenarios.
Need to check novelty before this filing date? Find Prior Art