FS-Net: A Flow Sequence Network For Encrypted Traffic Classification
FS-Net: сеть последовательностей потоков для классификации зашифрованного трафика
2019-04-01
SCID: 54.1/banvfusv
Discuss with AI
Flow Sequence Networkencoder-decoder architectureencrypted traffic classificationrecurrent neural networktraffic flow reconstruction
Figures from the paper
Abstract (AI)
With more attention paid to user privacy and communication security, the volume of encrypted traffic rises sharply, which brings a huge challenge to traditional rule-based traffic classification methods. Combining machine learning algorithms and manual-design features has become the mainstream methods to solve this problem. However, these features depend on professional experience heavily, which needs lots of human effort. And these methods divide the encrypted traffic classification problem into piece-wise sub-problems, which could not guarantee the optimal solution. In this paper, we apply the recurrent neural network to the encrypted traffic classification problem and propose the Flow Sequence Network (FS-Net). The FS-Net is an end-to-end classification model that learns representative features from the raw flows, and then classifies them in a unified framework. Moreover, we adopt a multi-layer encoder-decoder structure which can mine the potential sequential characteristics of flows deeply, and import the reconstruction mechanism which can enhance the effectiveness of features. Our comprehensive experiments on the real-world dataset covering 18 applications indicate that FS-Net achieves an excellent performance (99.14% TPR, 0.05% FPR and 0.9906 FTF) and outperforms the state-of-the-art methods.
Key Findings
1
A reconstruction mechanism is incorporated to improve the effectiveness of learned flow representations.
2
FS-Net applies a recurrent neural network to encrypted traffic classification, replacing manually engineered features with end-to-end learning from raw flows.
3
FS-Net outperforms state-of-the-art encrypted traffic classification methods in comprehensive experiments.
4
On a real-world dataset covering 18 applications, FS-Net achieves 99.14% TPR, 0.05% FPR, and 0.9906 FTF.
5
The model uses a multi-layer encoder-decoder architecture to deeply capture sequential characteristics in encrypted traffic flows.
Research Object
encrypted network traffic flows from 18 real-world applications
Research Subject
their sequential characteristics and classification performance under an end-to-end flow-sequence model
Publication Details
Publication Date
2019-04-01
Journal
Publisher
ISSN
Cited by
659
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai7
Adam: A Method for Stochastic Optimization2014
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
Distributed Representations of Words and Phrases and their Compositionality2013
Improving neural networks by preventing co-adaptation of feature detectors2012
A survey of methods for encrypted traffic classification and analysis2015
Deep Packet: A Novel Approach For Encrypted Traffic Classification Using\n Deep Learning2017
Data Driven VRP: A Neural Network Model to Learn Hidden Preferences for VRP2021
Cited by11
ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification2022
A Novel Multimodal Deep Learning Framework for Encrypted Traffic Classification2022
Seeing Traffic Paths: Encrypted Traffic Classification With Path Signature Features2022
Rosetta: Enabling Robust TLS Encrypted Traffic Classification in Diverse Network Environments with TCP-Aware Traffic Augmentation2023
ATVITSC: A Novel Encrypted Traffic Classification Method Based on Deep Learning2024
Deep Learning for Encrypted Traffic Classification and Unknown Data Detection2022
Automatic Mobile App Identification From Encrypted Traffic With Hybrid Neural Networks2020
Incremental Learning for Mobile Encrypted Traffic Classification2021
FG-SAT: Efficient Flow Graph for Encrypted Traffic Classification Under Environment Shifts2025
MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification2025
Time Will Tell: Criss-Cross Transformer for Encrypted Traffic Analysis2026