A Novel Multimodal Deep Learning Framework for Encrypted Traffic Classification

Новая мультимодальная модель глубокого обучения для классификации зашифрованного трафика
Peng Lin, Kejiang Ye, Yishen Hu, Yanying Lin, Chengzhong Xu
2022-11-03

encrypted traffic classificationmultimodal deep learningraw bytes and length sequenceself-attention mechanismunsupervised pre-training
Traffic classification is essential for cybersecurity maintenance and network management, and has been widely used in QoS (Quality of Service) guarantees, intrusion detection, and other tasks. Recently, with the emergence of SSL/TLS encryption protocols in the modern Internet environment, the traditional payload-based classification methods are no longer effective. Some researchers have used machine learning methods to model the flow features of encrypted traffics (e.g. message type, length sequence, statistical features, etc.), and achieved good results in some cases. However, these high-level hand-designed features cannot be used for more fine-grained operations and may lead to the loss of important information, thus affecting the classification accuracy. To overcome this limitation, in this paper, we designed a novel multimodal deep learning framework for encrypted traffic classification called PEAN. PEAN uses the raw bytes and length sequence as the input, and uses the self-attention mechanism to learn the deep relationship among network packets in a biflow. Furthermore, unsupervised pre-training was introduced to enhance PEAN’s ability to characterize network packets. Experiments on a real trace set captured in a large data center demonstrate the effectiveness of PEAN, which achieves better results than the state-of-the-art methods.
1
Experiments on real traffic traces from a large data center show that PEAN outperforms state-of-the-art encrypted-traffic classification methods.
2
PEAN is a multimodal deep learning framework for encrypted traffic classification that uses raw bytes and packet-length sequences as inputs.
3
The framework applies self-attention to learn deep relationships among packets within a bidirectional flow.
4
Unsupervised pre-training is incorporated to improve PEAN’s ability to characterize network packets.
5
Using raw packet information addresses limitations of hand-designed high-level features, which may discard information and restrict fine-grained classification.

Encrypted network traffic flows (biflows) represented by raw bytes and packet length sequences

fine-grained traffic classification based on learned relationships among network packets

Publication Details
Publication Date
2022-11-03
Journal
Publisher
ISSN
Cited by
137
Access Type
Author Information
Authors
Peng Lin
Kejiang Ye
Yishen Hu
Yanying Lin
Chengzhong Xu
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%