Maleh, Yassine
Unknown Affiliation

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Enhancing IoT network defense: advanced intrusion detection via ensemble learning techniques El Hajla, Salah; Ennaji, El Mahfoud; Maleh, Yassine; Mounir, Soufyane
Indonesian Journal of Electrical Engineering and Computer Science Vol 35, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v35.i3.pp2010-2020

Abstract

The Internet of Things (IoT) has evolved significantly, automating daily activities by connecting numerous devices. However, this growth has increased cybersecurity threats, compromising data integrity. To address this, intrusion detection systems (IDSs) have been developed, mainly using predefined attack patterns. With rising cyber-attacks, improving IDS effectiveness is crucial, and machine learning is a key solution. This research enhances IDS capabilities by introducing binary attack identification and multiclass attack categorization for IoT traffic, aiming to improve IDS performance. Our framework uses the ‘BoT-IoT’ and ‘TON-IoT’ datasets, which include various IoT network traffic and cyber-attack scenarios, such as DDoS and data infiltration, to train machine learning and ensemble models. Specifically, it combines three machine learning models-decision tree, resilient backpropagation (RProp) multilayer perceptron (MLP), and logistic regression-into ensemble methods like voting and stacking to improve prediction accuracy and reduce detection errors. These ensemble classifiers outperform individual models, demonstrating the benefit of diverse learning techniques. Our framework achieves high accuracy, with 99.99% for binary classification on the BoT-IoT dataset and 97.31% on the ToN-IoT dataset. For multiclass classification, it achieves 99.99% on BoT-IoT and 96.32% on ToN-IoT, significantly enhancing IDS effectiveness against IoT cybersecurity threats.
Adversarially robust federated deep learning models for intrusion detection in IoT Ennaji, El Mahfoud; El Hajla, Salah; Maleh, Yassine; Mounir, Soufyane
Indonesian Journal of Electrical Engineering and Computer Science Vol 37, No 2: February 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v37.i2.pp937-947

Abstract

Ensuring the robustness, security, and privacy of machine learning is a pivotal objective, crucial for unlocking the complete potential of the internet of things (IoT). Deep neural networks have proven to be vulnerable to adversarial perturbations imperceptible to humans. These perturbations can give rise to adversarial attacks, leading to erroneous predictions by deep neural networks, particularly in intrusion detection within the IoT environment. This paper introduces a federated adversarial learning framework designed to protect both data privacy and deep neural network models. This framework consists of federated learning for data privacy and adversarial training on IoT devices to enhance model robustness. The experiments show that adversarial training at the Fog node devices significantly improves the robustness of a federated learning model against adversarial attacks when compared to normal training. Furthermore, the proposed adversarial deep federated learning model is validated using the Edge-IIoTset dataset, achieving an accuracy rate of 91.23% in the detection of attacks.
Enhancing malware detection capabilities using deep learning with advanced hyperparameter tuning El Mouhtadi, Walid; Maleh, Yassine; Mounir, Soufyane
Indonesian Journal of Electrical Engineering and Computer Science Vol 37, No 2: February 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v37.i2.pp985-994

Abstract

As the threat landscape evolves with sophisticated malware and advanced persistent threats (APTs), the need for effective detection solutions increases. Traditional methods, such as signature-based and heuristic analysis, struggle to keep up with rapidly changing malicious activities. While machine learning offers a promising approach, it often falls short due to the manual extraction and selection of features, leading to time-consuming and error-prone processes. This research introduces a novel malware detection solution leveraging deep learning and focusing on portable executable (PE) file analysis to address these weaknesses. By customizing the hyperparameters of artificial neural networks (ANN), convolutional neural networks (CNN), and recurrent neural networks (RNN), the proposed approach enhances detection capabilities. The primary objective is to overcome the limitations of traditional and machine learning methods by tailoring these deep learning algorithms. The methodology includes a comparative study to demonstrate the advantages of the customized approach over conventional methods. Key findings reveal the proposed solution’s superior performance, accuracy, and adaptability in combating evolving cyber threats. This research contributes to the development of robust and adaptive malware detection solutions.