☆ 4.8 Article

Two-Stage Distillation-Aware Compressed Models for Traffic Classification

IEEE INTERNET OF THINGS JOURNAL (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Hardware & Architecture

Inferring Hidden IoT Devices and User Interactions via Spatial-Temporal Traffic Fingerprinting

Xiaobo Ma et al.

Summary: This paper introduces an efficient and scalable system that can accurately identify IoT devices in a network, infer the number of devices hidden behind NAT, and detect user interactions using spatial-temporal traffic fingerprinting. The system demonstrates high accuracy and low error rates in evaluation, showing promising potential in detecting user interactions.

IEEE-ACM TRANSACTIONS ON NETWORKING (2022)

Add to Collection

Article Computer Science, Information Systems

FLAG: Few-Shot Latent Dirichlet Generative Learning for Semantic-Aware Traffic Detection

Tianpeng Ye et al.

Summary: This paper proposes a Few-shot Latent Dirichlet Generative Learning (FLAG) scheme for semantic-aware traffic detection. By using a pseudo sample generation algorithm based on Latent Dirichlet Allocation (LDA) and a Fuzziness Recycle Method (FRM), efficient detection with few-shot samples is achieved and the accuracy of traffic classification is improved.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2022)

Add to Collection

Article Computer Science, Information Systems

Malware Traffic Classification Using Domain Adaptation and Ladder Network for Secure Industrial Internet of Things

Jinhui Ning et al.

Summary: This article proposes three methods based on semi-supervised learning, transfer learning, and domain adaptive to improve the accuracy of malware traffic classification in Industrial Internet of Things using a large amount of unlabeled data. Experimental results demonstrate the satisfactory performance of these methods in the case of few labeled samples.

IEEE INTERNET OF THINGS JOURNAL (2022)

Add to Collection

Proceedings Paper Telecommunications

Lightweight Models for Traffic Classification: A Two-Step Distillation Approach

Min Lu et al.

Summary: This research focuses on the task of traffic classification, which involves identifying different types of internet traffic or applications. Traditional methods have limitations in terms of predefining features and accuracy when faced with new applications. The study proposes a novel compressed model based on a two-step distillation approach to address these challenges.

IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022) (2022)

Add to Collection

Article Computer Science, Hardware & Architecture

Network traffic classification using deep convolutional recurrent autoencoder neural networks for spatial-temporal features extraction

Gianni D'Angelo et al.

Summary: The main aim of this work is to support modern network traffic classification methods by mining more expressive and meaningful features from basic features using a novel deep neural network architecture. Through experiments and theoretical analysis, it is demonstrated that the traffic classifier obtained by stacking autoencoder with a fully connected neural network significantly improves accuracy compared to existing machine learning approaches, pure convolutional and recurrent stacked neural networks, and pure feed-forward networks. This classifier is also able to maintain high accuracy even with imbalanced training datasets.

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS (2021)

Add to Collection

Article Engineering, Civil

A Survey of Deep Learning Applications to Autonomous Vehicle Control

Sampo Kuutti et al.

Summary: Deep learning methods have shown great promise in providing excellent performance for complex and non-linear control problems, as well as generalising previously learned rules to new scenarios. While there have been important advancements in using deep learning for vehicle control, there are still challenges to overcome, such as computation, architecture selection, goal specification, generalisation, verification and validation, as well as safety.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A Survey of the Usages of Deep Learning for Natural Language Processing

Daniel W. Otter et al.

Summary: This article provides a brief introduction to the recent developments in natural language processing driven by deep learning models, discusses their applications and research findings, and offers recommendations for future research directions.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

Add to Collection

Article Computer Science, Information Systems

A Blockchain-Driven IIoT Traffic Classification Service for Edge Computing

Heng Qi et al.

Summary: The article introduces a method of designing a lightweight traffic classification service in Industrial Internet of Things using hash mechanism and blockchain consensus mechanism. Through extension hashing and voting-based consensus algorithm to achieve efficient and accurate traffic classification, adapting to edge computing paradigm, improves classification accuracy, and reduces time cost and memory usage.

IEEE INTERNET OF THINGS JOURNAL (2021)

Add to Collection

Article Engineering, Multidisciplinary

Countering Machine-Learning Classification of Applications by Equalizing Network Traffic Statistics

Sina Fathi-Kazerooni et al.

Summary: This study suggests equalizing primary statistical metrics to decrease adversarial classification accuracy of network traffic classifiers, evaluates the identification process of user applications using different primary traffic metrics, and compares the performance of various ML algorithms in this classification task.

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING (2021)

Add to Collection

Proceedings Paper Computer Science, Theory & Methods

A Deep Learning based Traffic Flow Classification with Just a Few Packets

Ashish Gupta et al.

Summary: This paper proposes a deep learning-based model for traffic flow classification that significantly improves classification accuracy by using only a few packets and hand-crafted features, showing promising results in experiments.

IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (IEEE INFOCOM WKSHPS 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Flow Transformer: A Novel Anonymity Network Traffic Classifier with Attention Mechanism

Ruijie Zhao et al.

Summary: Supervising anonymity network is crucial in network security field. Traditional traffic analysis methods are ineffective against complex anonymity traffic. Deep learning-based traffic analysis methods have proven effective, but many studies overlook temporal-spatial correlation of traffic. The proposed FLOW TRANSFORMER classifier effectively handles anonymity traffic by utilizing multi-head attention mechanism and RF-based feature selection, outperforming existing methods significantly in real-world datasets.

2021 17TH INTERNATIONAL CONFERENCE ON MOBILITY, SENSING AND NETWORKING (MSN 2021) (2021)

Add to Collection

Proceedings Paper Engineering, Electrical & Electronic

Machine Learning Algorithm in Network Traffic Classification

Syifa Maliah Rachmawati et al.

Summary: This survey paper introduces the emerging research and general framework for deep learning-based methods for traffic classification. Deep learning methods are shown to provide better accuracy and automatic feature learning capabilities compared to traditional machine learning methods.

12TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE (ICTC 2021): BEYOND THE PANDEMIC ERA WITH ICT CONVERGENCE INNOVATION (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Multiresolution Knowledge Distillation for Anomaly Detection

Mohammadreza Salehi et al.

Summary: Unsupervised representation learning is crucial for anomaly detection/localization in images, facing challenges of small sample sizes and the need for discriminative features between normal and anomalous samples. Distilling features from an expert network pre-trained on ImageNet into a simpler cloner network can address these issues effectively. Incorporating multiple intermediate hints in distillation enables better utilization of expert knowledge and a more distinctive discrepancy between the networks.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Compressed Network in Network Models for Traffic Classification

Min Lu et al.

Summary: This study introduces a compressed NIN model for traffic identification, trained using a stepwise pruning and knowledge distillation approach to reduce storage and computing resources. Experimental results show that the minimum model can save significant parameters and computation time without compromising classification accuracy.

2021 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC) (2021)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Efficient Traffic Classification Using Hybrid Deep Learning

Farnaz Sarhangian et al.

Summary: Network traffic classification plays a crucial role in network management, requiring timely and accurate detection of specific traffic; Current methods include supervised and unsupervised learning, while traditional single classification models perform poorly on high-dimensional datasets, leading to a need for hybrid learning; This paper proposes two hybrid models based on the combination of CNN and RNN, achieving high accuracy on real datasets.

2021 15TH ANNUAL IEEE INTERNATIONAL SYSTEMS CONFERENCE (SYSCON 2021) (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Mathematical Validation of Proposed Machine Learning Classifier for Heterogeneous Traffic and Anomaly Detection

Azidine Guezzaz et al.

Summary: The study focuses on modeling and validating a heterogeneous traffic classifier for categorizing collected events within networks, aiming to address vulnerabilities in intrusion detection systems during the analysis and classification of data activities.

BIG DATA MINING AND ANALYTICS (2021)

Add to Collection

Article Computer Science, Theory & Methods

Accurate Decentralized Application Identification via Encrypted Traffic Analysis Using Graph Neural Networks

Meng Shen et al.

Summary: In this paper, a novel DApp fingerprinting method GraphDApp is proposed, utilizing Graph Neural Networks to turn DApp fingerprinting into a graph classification problem. Experimental results on traffic data from 1,300 DApps show that GraphDApp outperforms other methods in terms of classification accuracy.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

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

Mohammad Lotfollahi et al.

SOFT COMPUTING (2020)

Add to Collection

Article Computer Science, Information Systems

Computation Offloading with Multiple Agents in Edge-Computing-Supported IoT

Shihao Shen et al.

ACM TRANSACTIONS ON SENSOR NETWORKS (2020)

Add to Collection

Article Computer Science, Information Systems

AdaptFlow: Adaptive Flow Forwarding Scheme for Software-Defined Industrial Networks

Gagangeet Singh Aujla et al.

IEEE INTERNET OF THINGS JOURNAL (2020)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

Autonomous Unknown-Application Filtering and Labeling for DL-based Traffic Classifier Update

Jielun Zhang et al.

IEEE INFOCOM 2020 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (2020)

Add to Collection

Article Computer Science, Information Systems

Encrypted Network Traffic Classification Using Deep and Parallel Network-in-Network Models

Zhiyong Bu et al.

IEEE ACCESS (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Deep Learning for Encrypted Traffic Classification: An Overview

Shahbaz Rezaei et al.

IEEE COMMUNICATIONS MAGAZINE (2019)

Add to Collection

Article Geochemistry & Geophysics

Deep Learning for Hyperspectral Image Classification: An Overview

Shutao Li et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2019)

Add to Collection

Article Computer Science, Information Systems

Capsule Network Assisted IoT Traffic Classification Mechanism for Smart Cities

Haipeng Yao et al.

IEEE INTERNET OF THINGS JOURNAL (2019)

Add to Collection

Article Computer Science, Information Systems

Towards the Deployment of Machine Learning Solutions in Network Traffic Classification: A Systematic Survey

Fannia Pacheco et al.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2019)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

Bayesian Neural Network based Encrypted Traffic Classification using Initial Handshake Packets

Jiwon Yang et al.

2019 49TH ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS - SUPPLEMENTAL VOL (DSN-S) (2019)

Add to Collection

Article Computer Science, Information Systems

Intelligent IoT Traffic Classification Using Novel Search Strategy for Fast-Based-Correlation Feature Selection in Industrial Environments

Santiago Egea et al.

IEEE INTERNET OF THINGS JOURNAL (2018)

Add to Collection

Article Computer Science, Information Systems

Network Traffic Classifier With Convolutional and Recurrent Neural Networks for Internet of Things

Manuel Lopez-Martin et al.

IEEE ACCESS (2017)

Add to Collection

Article Computer Science, Information Systems

A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection

Anna L. Buczak et al.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2016)

Add to Collection

Article Computer Science, Information Systems

A multilevel taxonomy and requirements for an optimal traffic-classification model

Jawad Khalife et al.

INTERNATIONAL JOURNAL OF NETWORK MANAGEMENT (2014)

Add to Collection

Article Computer Science, Hardware & Architecture

Issues and Future Directions in Traffic Classification

Alberto Dainotti et al.

IEEE NETWORK (2012)

Add to Collection

Article Computer Science, Hardware & Architecture

Deep packet inspection tools and techniques in commodity platforms: Challenges and trends

Rafael Antonello et al.

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS (2012)

Add to Collection

© Peeref 2019-2024. All rights reserved.