| Titre : | A deep learning approach for intrusion detection in Vehicular Networks |
| Auteurs : | ILYES TIAR, Auteur ; Salim Bitam, Directeur de thèse |
| Type de document : | Monographie imprimée |
| Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2021 |
| Format : | 1 vol. (52 p.) / ill. / 29 cm |
| Langues: | Anglais |
| Mots-clés: | MANET, VANET, intrusion, Intrusion Detection System, Deep Learning,LSTM. |
| Résumé : |
he VANET network (Vehicular Ad- hoc Network) is a new technology fonts part of the family of mobile networks MANET. These networks are used to meet the communication requirements applied to transmission systems to improve driving and road safety to road users.VANETs properties offer significant challenges, making them open to several research
areas; among these areas of information exchange security. Intrusion detection systems (IDS),which are tools for the detection of attempted attacks on a network.In this work we aim to develop a deep learning approach for intrusion detection in VANETs using LSTM model and VeReMi dataset.The proposed approach consists of training an LSTM model to classify and predict potential intrusions in VANETs.The obtained results are very interesting and prove the efficiency and the effectiveness of the LSTM model. |
| Sommaire : |
General Introduction............................................................................. 1
1. Chapter 1 : Basic notions................................................................................... 3 1.1. Introduction ....................................................................... 3 1.2. Vehicular ad hoc Networks .............................................................................. 3 1.2.1. Definition:......................................................................... 3 1.2.2. Communication modes:.............................................................................. 5 1.2.3. Application for Vehicular Networks: ......................................................... 5 1.2.4. Standards and protocols for VANETs:....................................................... 6 1.3. Intrusion Detection System (IDS) : .................................................................. 8 1.3.1. Definition:........................................................................... 8 1.3.2. Detection methodologies:........................................................................... 8 1.4. Machine and Deep Learning: ........................................................................... 8 1.4.1. Machine Learning:...................................................................................... 8 1.4.2. Neural Networks and Deep Learning:...................................................... 11 1.4.3. Deep Learning for IDS ............................................................................. 19 1.5. Conclusion......................................................................... 19 2. Chapter 2 : Related Work ............................................................................... 20 2.1 Introduction .......................................................................... 20 2.2. DeepVCM (Zeng19): a Deep Learning Based Intrusion Detection Method in VANET: 20 2.2.1. Principle:................................................................... 20 2.2.2. Datasets: ..................................................................... 21 2.2.3. Discussion: ............................................................................................... 21 2.3. Collaborative Intrusion Detection for VANETs (Shu20): A Deep LearningBased Distributed SDN Approach........................................................................................ 22 2.3.1. Principle............................................................. 22 2.3.2. Dataset.................................................................... 22 2.3.3. Discussion................................................................................................. 23 2.4. Distributed Privacy-Preserving Collaborative intrusion Detection Systems For VANETs (Zhang18): ............................................................................ 24 2.4.1. Principle........................................................................ 24 2.4.2. Dataset.......................................................................... 24 2.4.3. Discussion..................................................................................... 24 2.5. Conclusion...................................................................... 25 3. Chapter 3: Design of our proposal.................................................................. 26 3.1 Introduction ........................................................................... 26 3.2 Methodology................................................................................................... 26 3.2.1 Dataset description .................................................................................... 27 3.2.2 Preprocessing............................................................................................. 28 3.2.3 LSTM learning .......................................................................................... 28 3.2.4 Test ................................................................... 30 3.2.5 Prediction...................................................................... 30 3.3. Conclusion......................................................... 30 4. Chapter 4: Implementation and results......................................................... 31 4.1. Introduction ........................................................... 31 4.2. Implementation frameworks and tools........................................................... 31 4.2.1. Python............................................................. 31 4.2.2. Anaconda.................................................................................................. 32 4.2.3. Tensorflow................................................................................................ 32 4.2.4. Keras....................................................................... 32 4.2.5. Jupyter Notebook...................................................................................... 33 4.2.6. Model evaluation metrics......................................................................... 33 4.2.7. Matplotlib ............................................................. 34 4.3. Implementation phases................................................................................... 35 4.3.1. Loading and preprocessing the dataset..................................................... 35 4.3.2. Creating the model ................................................................................... 36 4.3.3. Training the model ................................................................................... 38 4.4. Experiments and results.................................................................................. 38 4.5. Conclusion.................................................................. 41 Conclusion and future work...................................................................................... 42 References ............................................................................. 43 |
| Type de document : | Mémoire master |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| MINF/651 | Mémoire master | bibliothèque sciences exactes | Empruntable |
