Publications Scientifiques

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10

Browse

Author: search.filters.author.Riahla, Mohamed AmineHas files: Yes

Search Results

Now showing 1 - 10 of 11
  • Thumbnail Image
    Item
    Towards Blockchain-Based GDPR-Compliant spontaneous and ephemeral social network
    (Institute of Electrical and Electronics Engineers, 2025) Yahiatene, Youcef; Rachedi, Abderrezak; Riahla, Mohamed Amine
    Online Social Networks (OSNs) have rapidly integrated into our daily lives since their emergence in 2004, primarily serving as platforms for sharing personal information. This paper introduces a novel category of social networks: Spontaneous and Ephemeral Social Networks (SESNs). Unlike traditional OSNs, SESNs are event-centric, facilitating real-time connections and content sharing among participants within specific contexts. The main objective of SESNs is to improve the production, sharing, and consumption of digital content among network members. SESNs operate on a distributed peer-to-peer architecture using ad hoc mobile networks, leveraging the capability of mobile devices to communicate directly with each other in peer-to-peer mode. SESNs are ephemeral by nature, dissolving once participants disperse from the event location. However, for future analysis, some content may be retrievable from an external server after the event. A potential concern is that collaborative content creation within SESNs resembles crowdsourcing. However, in SESNs, the service provider may retain control over the data even after the event concludes. This centralized management of user-generated content could pose risks to user anonymity. To address these concerns, we propose a blockchain-based architecture that certifies transactions and ensures data anonymity in a decentralized manner. The proposed architecture demonstrates its robustness through a performance evaluation and a comprehensive security analysis. Our solution guarantees data integrity, confidentiality, privacy, anonymity, and network resilience. Additionally, blockchain technology is employed to ensure SESN compliance with the General Data Protection Regulation (GDPR).
  • Thumbnail Image
    Item
    Exploring Multi-Channel GPS Receivers for Detecting Spoofing Attacks on UAVs Using Machine Learning
    (Multidisciplinary Digital Publishing Institute, 2025) Mouzai, Mustapha; Riahla, Mohamed Amine; Keziou, Amor; Fouchal, Hacène
    All current transportation systems (vehicles, trucks, planes, etc.) rely on the Global Positioning System (GPS) as their main navigation technology. GPS receivers collect signals from multiple satellites and are able to provide more or less accurate positioning. For civilian applications, GPS signals are sent without any encryption system. For this reason, they are vulnerable to various attacks, and the most prevalent one is known as GPS spoofing. The main consequence is the loss of position monitoring, which may increase damage risks in terms of crashes or hijacking. In this study, we focus on UAV (unmanned aerial vehicle) positioning attacks. We first review numerous techniques for detecting and mitigating GPS spoofing attacks, finding that various types of attacks may occur. In the literature, many studies have focused on only one type of attack. We believe that targeting the study of many attacks is crucial for developing efficient mitigation mechanisms. Thus, we have explored a well-known datasetcontaining authentic UAV signals along with spoofed signals (with three types of attacked signals). As a main contribution, we propose a more interpretable approach to exploit the dataset by extracting individual mission sequences, handling non-stationary features, and converting the GPS raw data into a simplified structured format. Then, we design tree-based machine learning algorithms, namely decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost), for the purpose of classifying signal types and to recognize spoofing attacks. Our main findings are as follows: (a) random forest has significant capability in detecting and classifying GPS spoofing attacks, outperforming the other models. (b) We have been able to detect most types of attacks and distinguish them
  • Thumbnail Image
    Item
    Towards a Longitudinal Comparison Between Different Strategies for Android Malware Detection
    (Institute of Electrical and Electronics Engineers Inc, 2023) Mesbah, Abdelhak; Baddari, Ibtihel; Riahla, Mohamed Amine
    The growing popularity of the Android platform makes it a target of malware authors. The effective identification of such malware is an ongoing challenge. Several methods using machine learning have been proposed to prevent this threat. These methods are usually conventionally evaluated without considering the extent of performance over time. Given the evolving nature of both malware and benign apps, conventional evaluation may lack information. To imitate reality, this study compares the longitudinal performance of different machine learning models, using different strategies that combine permissions and API calls as features extracted through static analysis. Thus, to determine which strategy of features on which classifier are most effective to characterize malware for building a robust malware detector. To achieve this goal, on the one hand, we use a large real-world app set consisting of 100K (50k benign, 50k malware) apps date-labeled, collected across ten years, first seen between 2013 and 2022. On the other hand, each feature's strategy is fed into five classifiers (i.e., SVM, RF, LR, DT, and ANN), using old apps for the training and new apps for the evaluation. Among the assessed machine learning models, the SVM achieves the most promising results over time by employing the combination strategy of the high difference usage of API calls and permissions.
  • No Thumbnail Available
    Item
    Longcgdroid: android malware detection through longitudinal study for machine learning and deep learning
    (Scientific Research Support Fund of Jordan, 2023) Mesbah, Abdelhak; Baddari, Ibtihel; Riahla, Mohamed Amine
    This study aims to compare the longitudinal performance between machine-learning and deep-learning classifiers for Android malware detection, employing different levels of feature abstraction. Using a dataset of 200k Android apps labeled by date within a 10-year range (2013-2022), we propose the LongCGDroid, an image-based effective approach for Android malware detection. We use the semantic Call Graph API representation that is derived from the Control Flow Graph and Data Flow Graph to extract abstracted API calls. Thus, we evaluate the longitudinal performance of LongCGDroid against API changes. Different models are used; machine-learning models (LR, RF, KNN, SVM) and deep-learning models (CNN, RNN). Empirical experiments demonstrate a progressive decline in performance for all classifiers when evaluated on samples from later periods. However, the deep-learning CNN model under the class abstraction maintains a certain stability over time. In comparison with eight state-of-the-art approaches, LongCGDroid achieves higher accuracy.
  • No Thumbnail Available
    Item
    A distributed monitoring scheme for a fleet of UAV flying drones
    (2022) Nouasri, Amine; Riahla, Mohamed Amine
    In this paper, we present a solution that would allow members of a unmanned Arial vehicles (UAV) drone fleet to cooperate with each other in order to monitor the network regarding incidents that could compromise security or impact service continuity during their mission. The proposed work implements a scheme to allow each drone to monitor the activity of immediate neighbours without a central control authority, and share that information. This is in order to decide of an action in case of a security incident or a degradation of their service has occurred. The purpose is to allow the network to be resilient and adopt itself to insure service continuity. The method we used allow the detection of incidents without the use of complex security and routing solutions, or the need to communicate back and forth with a central control authority. Our method uses four parameters to insure service continuity in the network: link quality, forwarding rate, checksum rate and mobility coordinates. This is to allow the detection of multiple incidents using the same scheme.
  • No Thumbnail Available
    Item
    A blockchain-based framework to secure vehicular social networks
    (wiley, 2019) Yahiatene, Youcef; Rachedi, Abderrezak; Riahla, Mohamed Amine; Menacer, Djamel Eddine; Nait-Abdesselam, Farid
    Vehicular social network is emerging as a new promising concept, combin-ing two types of network paradigms, namely, vehicular networks and socialnetworks. In order to manage efficiently the security and the control of the net-work, this paper proposes a new framework based on the emerging concepts ofsoftware-defined vehicular network (SDVN) and blockchain. Using the SDVNmakes the network more programmable, virtualized, and partitionable. How-ever, on the other hand, it also creates a well-known vulnerability of a singlepoint of failure. Hence, we propose to introduce the blockchain paradigm thatwill enable the certification of transactions and ensure data anonymity in afully distributed manner. To this end, three levels of controllers are needed: aprincipal controller (PC), roadside units (RSUs), and a local controller. In orderto dynamically select miners, a distributed miners connected dominating setalgorithm (DM-CDS) has been proposed. The DM-CDS is a single-phase dis-tributed algorithm that supports a dynamic topology based on a trust model andsome other network parameters, such as the connectivity degree, the averagelink quality indicator, and the rank. The performance of the proposed DM-CDSis evaluated throughout multiple scenarios using different parameters, such astrust metric, node density, node mobility, and radio range. The obtained resultshighlight the importance of such proposed architecture, especially in terms ofnumber of required miners. For instance, when the density of nodes increases,the number of selected miners increases similarly to when the network lengthincreases. The node mobility impacts also on the stability of the selected miners,in terms of withdrawing and joining, showing a variation between 0% and 10%.The trust metric has also an important impact on the selection of miners, as onlynodes with a higher trust level are selected to endorse the roles of miners.
  • No Thumbnail Available
    Item
    Towards a distributed ABE based approach toprotect privacy on online social networks
    (IEEE, 2019) Yahiatene, Youcef; Menacer, Djamel Eddine; Riahla, Mohamed Amine; Rachedi, Abderrezak; Tebibel, Thouraya Bouabana
    In this paper, we present a new framework for protecting privacy on online social networks based on two main concepts: cloud computing and Attribute-Based Encryption system (ABE). The cloud computing is used to store outsourcing data by a third party. However, the issues of entrusting these third-party losing control over data arise. Thus, one does not know where data are stored. In the proposed framework we propose to use a distributed multi-authority ABE scheme, which provides flexible access to private data, and only users with the right keys can have access to it. The performance evaluation is conducted by simulations with different parameters including the number of attributes, encryption time and decryption time. The obtained results and security analysis show that our solution outperforms the classical solutions in terms of security and robustness.
  • No Thumbnail Available
    Item
    A summary of the existing challenges in the design of a routing protocol in UAVs network
    (IEEE, 2020) Boutalbi, Mohammed Chaker; Riahla, Mohamed Amine; Ahriche, Aimad
    The difficulties in the routing mechanism in UAV's networks are taking interest in these last years. The challenge is still up to come up with full solutions for the developed constraints that have been raised with the high dynamicity and link disconnections in this type of ad hoc network. Large and detailed surveys have been proposed in the literature, where they essentially focus on the taxonomy of a vast number of proposed solutions. Based on this, and from a different angle of view, in this paper, we summarize the existing challenges in the design of a routing protocol for UAVs network. Unlike the other works, our approach focuses on collecting and illustrating all routing constraints that a drone can face in the decision-making process, also, we argue on how an appropriate design of a FANET routing protocol should be to provide a generic and efficient evaluation platform for future works.
  • No Thumbnail Available
    Item
    A new AOMDV lifetime prolonging routing algorithm for Ad-Hoc networks
    (IGI Global, 2019) Baddari, Ibtihel; Riahla, Mohamed Amine; Mezghiche, Mohamed
    Network lifetime is a key design metric in MANETs, it is considered as one of the most important parametersalgorithmstobeusedinadhocnetworks.Eachnetworknodeworkscompletely independently and acts as a router for relaying communications. If some nodes die prematurely because of battery depletion, the network lifetime will be adversely affected, and the network will get disconnected. This article presents AOMDV-LP, a new AOMDV lifetime-prolonging routing algorithm for MANETs. This new algorithm helps to maximize the network lifetime by managing nodesenergy,linkcostandcontrollingthenetworkscongestion.Simulationsquantifytheperformance gains of the authors algorithm
  • No Thumbnail Available
    Item
    A multipath Lifetime-Prolonging routing algorithm for wireless ad hoc networks
    (SAI Organization, 2016) Riahla, Mohamed Amine; Tamine, Karim
    Dynamic networks can be tremendously challenging when deploying distributed applications on autonomous machines. Further, implementing services like routing and security for such networks is generally difficult and problematic. Consequently, multi-agent systems are well suited for designing distributed systems where several autonomous agents interact or work together to perform a set of tasks or satisfy a set of goals, hence moving the problem of analyzing from a global level to a local level therefore reducing the design complexity. In our previous paper, we presented a Multi Agent system model that has been adapted to develop a routing protocol for ad hoc networks. Wireless ad hoc networks are infrastructureless networks that comprise wireless mobile nodes which areable to communicate with each other outside the wireless transmission range. Due to frequent network topology changes, the limited energy and underlying bandwidth, routing becomes a challenging task. In this paper, we present a new version of routing algorithm devoted for mobile ad hoc networks. Our new algorithm helps controlling the network congestion and increasing the network lifetime by effectively managing nodes energy and link cost. The performance of our new version is validated through simulation. The Simulation results show the effectiveness and efficiency of our new algorithm compared to stae-of-the-artsolutions in terms of various performance metrics