• Corpus ID: 246822422

A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification

@article{Fauvel2022ALE,
  title={A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification},
  author={Kevin Fauvel and Alessandro Finamore and Lixuan Yang and Fuxing Chen and Dario Rossi},
  journal={ArXiv},
  year={2022},
  volume={abs/2202.05535}
}
Traffic classification, i.e. the identification of the type of applications flowing in a network, is a strategic task for numerous activities (e.g., intrusion detection, routing). This task faces some critical challenges that current deep learning approaches do not address. The design of current approaches do not take into consideration the fact that networking hardware (e.g., routers) often runs with limited computational resources. Further, they do not meet the need for faithful explainability… 

Figures and Tables from this paper

Research Article Lightweight Traffic Classification Model Based on Deep Learning

This work proposes a lightweight tra ffi c classi fi cation model based on the Mobilenetv3 and improves it for an ingenious balance between performance and lightweight and embeds precise spatial information on the attention mechanism to enhance the trafl c fl ow-level feature extraction capability.

Lightweight Traffic Classification Model Based on Deep Learning

This work proposes a lightweight traffic classification model based on the Mobilenetv3 and improves it for an ingenious balance between performance and lightweight and embeds precise spatial information on the attention mechanism to enhance the traffic flow-level feature extraction capability.

DA-Transfer: A Transfer Method for Malicious Network Traffic Classification with Small Sample Problem

The proposed DA-Transfer method significantly improves the accuracy and efficiency of the small-sample malicious traffic classification model by integrating both data and model transfer adaptive modules.

References

SHOWING 1-10 OF 63 REFERENCES

Mobile Encrypted Traffic Classification Using Deep Learning: Experimental Evaluation, Lessons Learned, and Challenges

Different state-of-the-art DL techniques from (standard) TC are reproduced, dissected, and set into a systematic framework for comparison, including also a performance evaluation workbench, to propose deep learning classifiers based on automatically extracted features, able to cope with encrypted traffic, and reflecting their complex traffic patterns.

Toward effective mobile encrypted traffic classification through deep learning

Deep packet: a novel approach for encrypted traffic classification using deep learning

Deep Packet can identify encrypted traffic and also distinguishes between VPN and non-VPN network traffic, and outperforms all of the proposed classification methods on UNB ISCX VPN-nonVPN dataset.

Opening the Deep Pandora Box: Explainable Traffic Classification

In this demonstration, light is shed in the inference process of a commercial-grade classification engine dealing with hundreds of classes, enriching the classification workflow with tools to enable better understanding of the inner mechanics of both the traffic and the models.

XAI Meets Mobile Traffic Classification: Understanding and Improving Multimodal Deep Learning Architectures

This work investigates trustworthiness and interpretability via XAI-based techniques to understand, interpret and improve the behavior of state-of-the-art multimodal DL traffic classifiers.

FS-Net: A Flow Sequence Network For Encrypted Traffic Classification

The recurrent neural network is applied to the encrypted traffic classification problem and the Flow Sequence Network (FS-Net) is proposed, an end-to-end classification model that learns representative features from the raw flows, and then classifies them in a unified framework.

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

This work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs, and derives several practical guidelines for efficient network design, called ShuffleNet V2.

Large-Scale Mobile App Identification Using Deep Learning

A CNN+LSTM model that uses adjacent flows to learn the order and pattern of multiple flows, to better identify the app that generates them, and it is shown that such flow association considerably improves the accuracy, particularly for ambiguous flows.

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

A new scaling method is proposed that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient and is demonstrated the effectiveness of this method on scaling up MobileNets and ResNet.
...