Machine learning for networking : 4th international conference, MLN 2021, virtual event, December 1-3, 2021 : proceedings / edited by Éric Renault, Selma Boumerdassi, Paul Mühlethaler.

Format:

Book

Contributor:

Boumerdassi, Selma, editor.

Mühlethaler, Paul, editor.

Renault, Eric, editor.

Series:

Lecture Notes in Computer Science

Lecture Notes in Computer Science ; v.13175

Language:

English

Subjects (All):

Machine learning.

Physical Description:

1 online resource (171 pages)

Edition:

1st ed.

Place of Publication:

Cham, Switzerland : Springer, [2022]

Summary:

This book constitutes the thoroughly refereed proceedings of the 4th International Conference on Machine Learning for Networking, MLN 2021, held in Paris, France, in December 2021.The 10 revised full papers included in the volume were carefully reviewed and selected from 30 submissions.

Contents:

Intro

Preface

Organization

Contents

Evaluation of Machine Learning Methods for Image Classification: A Case Study of Facility Surface Damage

1 Introduction

2 Research Methodology

2.1 Maximum Likelihood

2.2 Random Forest

2.3 Evaluation Index of Classification Model

3 Analytical Results

4 Conclusion

References

One-Dimensional Convolutional Neural Network for Detection and Mitigation of DDoS Attacks in SDN

2 Related Work

3 One Dimensional Convolutional Neural Network (1D-CNN)

4 Proposed Approach

4.1 CICDDoS2019 Dataset

4.2 Dataset Manipulation

4.3 Proposed 1D-CNN Architecture

5 Evaluation and Analysis

5.1 1D-CNN Evaluation Criteria

5.2 Effectiveness for Applying 1D-CNN in SDN

6 Conclusion

Multi-Armed Bandit-Based Channel Hopping: Implementation on Embedded Devices

2 Background

3 Further MAB Algorithms

4 SW-UCB and D-UCB Under Constraints

4.1 Relevant Fixed-Point Arithmetic

4.2 Implementation Shortcuts

4.3 Integration into IEEE 802.15.4 CSL

5 Evaluation

5.1 Monte Carlo Simulations

5.2 Real-World Packet Delivery Ratios

5.3 Overhead on CC2538 SoCs

6 Conclusions and Future Work

Cross Inference of Throughput Profiles Using Micro Kernel Network Method

1.1 Profiles from Network Emulations

1.2 Contributions

2 TCP Throughput Profile

3 mKN-ML Method

4 Testbed and Emulation Measurements

4.1 Testbed Measurements

4.2 Mininet mKN Measurements

4.3 Multi-site Federation: Mininet Emulation

5 Estimated Profiles

5.1 mKN Generic RTT Set: Concave Target Profiles

5.2 VFSIE Measurements: Concave Target Profiles

5.3 Exploratory Scenario Profiles

6 Generalization Equations

7 Conclusions

References.

Machine Learning Models for Malicious Traffic Detection in IoT Networks /IoT-23 Dataset/

2 Review of the Related Works

2.1 Traditional Methods for Network Traffic Analysis

2.2 Approaches to Detecting IoT Malicious Traffic Using Machine Learning

3 IoT 23 Dataset

3.1 Description of IoT-23 Dataset

3.2 Data Engineering

4 Preprocessing

5 Models

5.1 Decision Tree Classifier

5.2 Logistic Regression

5.3 Random Forest Classifier

5.4 XGBoost Classifier

5.5 Artificial Neural Networks

6 Results

7 Discussion

8 Conclusion

Application and Mitigation of the Evasion Attack against a Deep Learning Based IDS for IoT

2.1 Deep Learning IDS

2.2 Evasion Attack

2.3 Adversarial Attack Defense

3 Proposed Evasion Attack Strategy

3.1 Oracle Evasion Attack

3.2 Modified FGSM

4 Defense Strategy

4.1 Adversarial Example Training

4.2 Outlier Detection

5 Validation Results

6 Conclusions

DynamicDeepFlow: An Approach for Identifying Changes in Network Traffic Flow Using Unsupervised Clustering

3 Motivation

4 Building DynamicDeepFlow Neural Network

4.1 Input and Output Structures

4.2 Overall Architecture of DDF

4.3 Training Algorithm

5 Experimental Data and Implementation Details

5.1 Experimental Data

5.2 Experimental Setup

5.3 Implementation Details

6.1 Anomalous Network Traffic Pattern Identification

6.2 Sensitivity to Number of Cluster

6.3 Visualization of VAE Features

7 Conclusion

Unsupervised Anomaly Detection Using a New Knowledge Graph Model for Network Activity and Events

3 AEN Graph Model Overview

4 Proposed Anomaly Detection Model

4.1 Measure of Anomalousness.

4.2 Features Model

5 Experimental Evaluation

5.1 Dataset

5.2 Performance Evaluation

Deep Reinforcement Learning for Cost-Effective Controller Placement in Software-Defined Multihop Wireless Networking

3 System Model

4 Experiments, Results and Analysis

5 Conclusion and Future Research

Distance Estimation Using LoRa and Neural Networks

2 LoRa Technology

3 Related Work

4 Neural Network

5 Experimental Setup

6 Results and Analysis

Author Index.

Notes:

Includes bibliographical references and index.

Description based on print version record.

Description based on publisher supplied metadata and other sources.

Other Format:

Print version: Renault, Éric Machine Learning for Networking

ISBN:

3-030-98978-X

OCLC:

1305436069