Research Interests:
Research Interests:
In recent times, malware visualization has become very popular for malwareclassification in cybersecurity. Existing malware features can easily identifyknown malware that have been already detected, but they cannot identify newand... more
In recent times, malware visualization has become very popular for malwareclassification in cybersecurity. Existing malware features can easily identifyknown malware that have been already detected, but they cannot identify newand infrequent malwares accurately. Moreover, deep learning algorithmsshow their power in term of malware classification topic. However, we foundthe use of imbalanced data; the Malimg database which contains 25 malwarefamilies don’t have same or near number of images per class. To address theseissues, this paper proposes an effective malware classifier, based on costsensitive deep learning. When performing classification on imbalanced data, some classes get less accuracy than others. Cost-sensitive is meant to solve this issue, however in our case of 25 classes, classical cost-sensitive weights wasn’t effective is giving equal attention to all classes. The proposed approach improves the performance of malware classification, and we demonstrate this improvement...
The Smart cities are a relevant topic nowadays. It attracts most researchers and governmental authorities, due to the vision to adopt technology information and communication in this context, to facilitate access to urban services.... more
The Smart cities are a relevant topic nowadays. It attracts most researchers and governmental authorities, due to the vision to adopt technology information and communication in this context, to facilitate access to urban services. Security stills a permanent challenge that affects most smart cities applications. Vehicular Ad Hoc Networks (VANets) is one of those applications, classified in the smart mobility axis. VANets are certainly affected by security risks faced to the users. The GPS (Global Positioning System) who widely used in several applications of human life is vulnerable to different attacks like jamming, blocking and spoofing. The last attack tries to provide to the receiver fake information, and because of this, it computes an wrong time or location. In this paper we study the impact of spoofing attack on VANets communications. Because of this, our work presented here, is focused on claiming the attack of GPS cars signal and smart phones. The paper studies the vulnerabilities of those signals face to the fake GPS that can distract drivers. This can, consequently, affect people security and congestion in roads of the cities. We perform an experiment in a relevant indoor scenario, using arduino devices for real simulation to see the impact of the attack on vehicles circulation.
Research Interests:
Research Interests:
Mobile Ad Hoc network (MANET) is a collection of smart mobile nodes, which form a dynamic and autonomous system. Since mobile nodes are free to move, they cause frequent changes in network topology and decrease the overall network... more
Mobile Ad Hoc network (MANET) is a collection of smart mobile nodes, which form a dynamic and autonomous system. Since mobile nodes are free to move, they cause frequent changes in network topology and decrease the overall network performances. Therefore, the task of finding and maintaining a reliable route constitute the main issue in the design of efficient routing protocol for MANET. In this paper, we introduce a novel Mobility Adaptive AODV routing protocol (MA-AODV), which uses the degree of mobility time variation and the local route repair approach to mitigate the influence of high mobility and improve routing performances. We implemented the MA-AODV on network simulator NS2. Then, we evaluated the performance of MA-AODV and AODV based on node mobility variation such as speed and pause time. The comparison of performance metrics, such as Packet delivery Ratio, Throughput, routing overhead and communication delay demonstrates that MA-AODV outperforms AODV in high mobility envi...
Mobile Ad Hoc network (MANET) is a collection of smart mobile nodes, which form a dynamic and autonomous system. These nodes communicate wirelessly in a self-organized, self-configured and self-administered manner. Routing protocol is the... more
Mobile Ad Hoc network (MANET) is a collection of smart mobile nodes, which form a dynamic and autonomous system. These nodes communicate wirelessly in a self-organized, self-configured and self-administered manner. Routing protocol is the main building block in route establishment and traffic delivery, which must be accomplished anywhere and anytime, between a pair of source and destination. Therefore, research interest in MANETs has been growing, and particularly the design of MANET routing protocols has gained a lot of interest. Furthermore, constantly changing network topology, limited bandwidth and energy issues make the task of routing in MANETs a challenging one. In this paper we provide the taxonomy of routing protocols for MANETs, which constitute the main key behind the design of routing protocols process.
Research Interests:
Even when 6LoWPAN has an ideal cryptography line defense, it is still necessary to implement an intrusion detection system (IDS) to deal with threats targeting network performance such as DoS attacks. IDS discover and stop most attacks... more
Even when 6LoWPAN has an ideal cryptography line defense, it is still necessary to implement an intrusion detection system (IDS) to deal with threats targeting network performance such as DoS attacks. IDS discover and stop most attacks that make changes on the operation of the network. However, few IDS solution has been proposed for 6LoWPAN networks. IDS missions are to monitor and raise an alarm about any possible threats and pass it to the system to restart the keying process for eliminating the attackers. New technique has been proposed recently based on the principle that neighbor nodes have a trend to have the same behavior, so the detection of the malicious node is based on the detection of the abnormal node that has a bad behavior different than it neighbors. The security goal is to provide a monitoring system that will attempt to detect anomalous malicious behavior and to prevent it from harming the network performance basing on the neighbors nodes behavior monitoring.
Research Interests:
Research Interests:
The adoption of digital technology in both learning and teaching process, and the evolution of information technologies are opening new perspectives for the use of augmented reality (AR) and virtual reality (VR). Thus, these technologies... more
The adoption of digital technology in both learning and teaching process, and the evolution of information technologies are opening new perspectives for the use of augmented reality (AR) and virtual reality (VR). Thus, these technologies can facilitate the assistance of learners working on complex learning situation by using AR and enable the implementation of VR trainings, thus improving their efficiency. However, integrating these new tools into the existing learning processes remains complex, due to the technological aspects and the data continuum to be implemented, through the identification of use cases and the associated gains and by the diversity actors and experts to involve in this process: the expert of the main field, the designer and the IT developer. In this paper we aim to develop an AR application by following a developing process that will led to the planned results. The proposed application will be dictated for learners in higher education context, especially newbies that will practice their first experiment in the laboratory e.g." biology, chemistry" by giving them an interactive environment to understand the safety procedure followed during experiments in laboratories.
Research Interests:
Voice over Internet Protocol (VoIP) may provide good services through Vehicular ad hoc networks (VANETs) platform by providing services to many application scenarios range from safety to comfort. However, VANETs networks introduce many... more
Voice over Internet Protocol (VoIP) may provide good services through Vehicular ad hoc networks (VANETs) platform by providing services to many application scenarios range from safety to comfort. However, VANETs networks introduce many challenges for supporting voice with QoS requirements. In this paper, our study is based on Inter-Vehicle voice streaming rely on multi-hop fashion. For this task, a performance evaluation of various audio CODECs will be analyzed by mean of simulations. Furthermore, we test the impact of network environment on QoS metrics. To achieve good results, CODECs behaviour is tested by using mobility information obtained from vehicular traffic generator. The mobility model is based on the real road maps of an urban environment. Focusing on inter-vehicular voice traffic quality, we provide simulations results in terms of both user level (MOS) metrics and network level (such as Losses). According to this performance evaluation, we show that G.723.1 CODEC worked ...
Serious Games start playing an important role in education [8]. Developed economies start using serious games for a variety of objectives among whish we find retraining the workforce, offering off-hours training in self-service mode,... more
Serious Games start playing an important role in education [8]. Developed economies start using serious games for a variety of objectives among whish we find retraining the workforce, offering off-hours training in self-service mode, supplementing teachers work with games appealing to young generations, and reducing training costs [6], [7]. Learning in these developed economies is based usually on active methods and serious games bring additional training activities to the learning process[14][15]. Learning in some developing countries is based on remembering and reciting mainly. Training schoolchildren on applying knowledge is a challenge for teachers in some developing countries. Developing countries can use serious games as a catalyst to train schoolchildren on applying knowledge. The development of such serious games for schoolchildren requires collaboration between pedagogues, game designers and software developers. In this paper, we present a process and a methodology to design and develop serious games for schoolchildren. This process is called Gaming and Learning Unified Process to engineer Software, or GLUPS. We present the foundations of GLUPS, list its main artifacts, and illustrate this paper with the application of GLUPS to design a serious game that train on applying the Euclidean Division.
Research Interests: Computer Science and Acm
Serious games combine pedagogy and interactive learning to foster high intrinsic motivation and positive player experience; they can increase participant interest and make the training process more enjoyable, memorable and effective. The... more
Serious games combine pedagogy and interactive learning to foster high intrinsic motivation and positive player experience; they can increase participant interest and make the training process more enjoyable, memorable and effective. The multi-layer model provides an approach to analyse and evaluate serious games design in a collaborative (designer, professional and player) and iterative process. In this paper, we propose a multi-layer methodology of serious games based on the design, play and experience framework (DPE) often used in instructional design, this methodology will help game designers, especially the beginners to analyses their own serious games easily, and will allow professionals to evaluate and provide a guideline of design in collaboration with several actors.
Research Interests:
Malicious software attacks cause serious loss to computer users, from personal usage to industrial networks. For this reason, researchers focused more and more on analyzing and detecting malware. Approaches found in literature can well... more
Malicious software attacks cause serious loss to computer users, from personal usage to industrial networks. For this reason, researchers focused more and more on analyzing and detecting malware. Approaches found in literature can well predict a new malware sample belonging to known families, but what about newborn families. In this paper, we perform malware classifiers based on two machine learning algorithms: Random forest and K-Nearest Neighbor. We used the malware visualization technique, so a malware binary is presented as a grayscale image. After that, we calculated the GIST descriptor features for all samples to be ready for the classification. Results obtained are, respectively, 97, 99%, and 98,21% for the two algorithms. Then, we study the behavior of our classifier in the case of new arrival family. Next, we get inspired from the COVID19 disease outbreak. So we proposed precautions to be made as security measures in case of new malware family appearance. With the goal to reduce damage causes by these kind of attacks.
Research Interests:
Serious Games are video-games designed to support learning and start playing a role in education. Serious games are used as an eLearning tool to complement traditional education or for distance learning. Researchers have tested serious... more
Serious Games are video-games designed to support learning and start playing a role in education. Serious games are used as an eLearning tool to complement traditional education or for distance learning. Researchers have tested serious games in preschools and primary schools recently, and results started proving efficiency. During the Covid19 study-from-home period in Morocco, we have developed a serious game for preschool to help practice logical reasoning and remembering. We have used a process to design and develop the serious game by a collaborative team. This process is based on a methodology called GLUPS (Serious Game Development Processes). During the development process, we had to adapt GLUPS to better fit with serious games for school children and with development carried by developers, not always familiar with game vocabulary and game development. GLUPS helped us produce a playable well featured serious game quickly.
Research Interests:
Research Interests:
Machine learning (ML) is a large field of study that overlaps with and inherits ideas from many related fields such as artificial intelligence (AI). The main focus of the field is learning from previous experiences. Classification in ML... more
Machine learning (ML) is a large field of study that overlaps with and inherits ideas from many related fields such as artificial intelligence (AI). The main focus of the field is learning from previous experiences. Classification in ML is a supervised learning method, in which the computer program learns from the data given to it and make new classifications. There are many different types of classification tasks in ML and dedicated approaches to modeling that may be used for each. For example, classification predictive modeling involves assigning a class label to input samples, binary classification refers to predicting one of two classes and multi-class classification involves predicting one of more than two categories. Recurrent Neural Networks (RNNs) are very powerful sequence models for classification problems, however, in this paper, we will use RNNs as generative models, which means they can learn the sequences of a problem and then generate entirely a new sequence for the p...
Research Interests:
Basically, serious games provides enjoyment and knowledge, several researches in this field have focused into joining these two proprieties and make the best balance between them, in order, to provide the best game and enjoyable game... more
Basically, serious games provides enjoyment and knowledge, several researches in this field have focused into joining these two proprieties and make the best balance between them, in order, to provide the best game and enjoyable game experience and ensure the learning of the needed knowledge. Players differ and their knowledge background can be a lot different from one to the other. This study focused on how the SG adapts and provide the needed knowledge and enjoyment. The game should analyze players behavior from different angles, thus it can add difficulty, information, immersion or enjoyment modules to fit the player skills/knowledge.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Medical staffs wear face masks to prevent the spread of the disease. Nowadays, with the coronavirus pandemic everyone must wear a facemask for the same reason. When a person near to you coughs, talks, sneezes he could release germs into... more
Medical staffs wear face masks to prevent the spread of the disease. Nowadays, with the coronavirus pandemic everyone must wear a facemask for the same reason. When a person near to you coughs, talks, sneezes he could release germs into the air that may infect you or anyone nearby. Wearing a facemask is a part of an infection control strategy to avoid and eliminate cross-contamination. Even so, people are getting tired of wearing facemasks or they are not conscious enough of the seriousness of the actual covid19. In this paper, we propose a facemask detector based on IoT embedded devices and deep learning algorithm. Our main goal is to warn people in real-time if they are not wearing a facemask or they are not wearing it correctly. The proposed solution generates loud vocal alerts after detection disrespect of facemask wear in real-time for a fast reaction. To have the most efficient detector in real-time we tested the facemask detection model using various versions of the Raspberry Pi and NCS2. As a result, the facemask detector works perfectly on powerful devices, however its performance decrease in realtime using less powerful devices such as an old version of the Raspberry Pi.
Research Interests:
Data will soon become one of the most precious treasures we have ever had, 43 trillion gigabytes of data will be created by 2020 according to a study made by Mckinsey Global Institute, it is estimated that 2.3 trillion gigabytes of data... more
Data will soon become one of the most precious treasures we have ever had, 43 trillion gigabytes of data will be created by 2020 according to a study made by Mckinsey Global Institute, it is estimated that 2.3 trillion gigabytes of data is created each day and most companies in the US have 100.000 gigabytes of data stored. Data is recorded, stored and analyzed to enable technology and services that the world relies on every day, this technology is getting smarter and we will be soon living in a world of smart services or what is called smart cities. This article presents an overview of the topic pointing to its actual status and forecasting the crucial roles it will play in the future, we will define big data analytics and smart cities and talk about their potential contributions in changing our way of living and finally we will discuss the possible down side of this upcoming technologies and how it can fool us, violate our privacy and turn us into puppets or technology slaves.
Research Interests:
With the big success that serious games have known in education field a huge need has been created to develop such video games in order to satisfy the demand that does not cease to increase, but the time, the cost, and the interaction of... more
With the big success that serious games have known in education field a huge need has been created to develop such video games in order to satisfy the demand that does not cease to increase, but the time, the cost, and the interaction of several actors during the creation process of video games can influence on the envisaged result and create several unexpected problems, to avoid such problems we propose in this article a new web-based serious games generator that adapts the process of video game development by replacing game design and game development phases by both programmed game design and gameplays, this new concept will allow the game creators to focus more in pedagogical aspect and pedagogical objectives that the players must acquire during a video game sequence, instead of wasting much time in game design and game development. In addition, the proposed game generator will be equipped with a fuzzy expert system to assist the users during the game generation process; the prop...
Research Interests:
Internet use is growing every day, accessing a website via its URL (Uniform Resource Locator) address is a daily task, but not all websites are benign to be accessed without any fear from malicious aims not matter where those websites are... more
Internet use is growing every day, accessing a website via its URL (Uniform Resource Locator) address is a daily task, but not all websites are benign to be accessed without any fear from malicious aims not matter where those websites are being accessed from (Web Browsers, e-mails body, chat application, SMS, VoIP) neither the nature of the operating system or the device. Our thesis aim is being able to detect the kind of websites that try to steal any user’s (normal users, communities, societies, laboratories, etc.) personal information like name, date of birth, e-mail, credentials, login and passwords from e-banking services for example or any other web services. Unlike traditional techniques that consists of penetrating data sources of web services providers by decrypting algorithms, the man idea of this kind of criminal activities is letting the victims give those informations unconsciously, by creating fake emails or websites that looks very similar of original ones and tell vi...
Research Interests:
In this paper, we propose a deep learning framework for malware classification. There was a big boom within the quantity of malware in current years which poses an extreme safety chance to financial establishments, agencies, and people.... more
In this paper, we propose a deep learning framework for malware classification. There was a big boom within the quantity of malware in current years which poses an extreme safety chance to financial establishments, agencies, and people. In order to fight the proliferation of malware, new techniques are essential to quickly perceive and classify malware samples so that their behavior can be analyzed. Machine learning methods are becoming famous for classifying malware, but, the maximum of the modern gadget gaining knowledge of strategies for malware classification use machine learning algorithms (e.g., SVM). Currently, Convolutional Neural Networks (CNN), a deep getting to know approach, have proven advanced performance in comparison to traditional getting to know algorithms, particularly in duties which include image classification. Influenced by way of this achievement, we recommend a CNN-based architecture to classify malware samples. We convert malware binaries to a grayscale image, and at the end, we train a CNN network for classification. Experiments on hard malware classification datasets, Malimg, and Microsoft malware, reveal that our technique achieves higher than the modern-day overall performance.
Research Interests:
Smartphones are advanced versions of cell phones which can provide multi functions tasks. Most Smartphones have the following facilities: E-mails, Cameras, Wi-Fi connectivity, and comprehensive user interface such as touch screen and... more
Smartphones are advanced versions of cell phones which can provide multi functions tasks. Most Smartphones have the following facilities: E-mails, Cameras, Wi-Fi connectivity, and comprehensive user interface such as touch screen and built in GPS system and interface for installing new applications. Using outdoor location-based services associated with GPS/GPRS have widely out broken. This paper aims at developing a velocity based system for location tracking that will be more convenient for users and more reliable, putting into consideration the expenses for the network service and increasing the accuracy in Smartphones.
Research Interests:
IEEE 802.15.4-based devices networks known by the name of LR-WPAN (Low Rate Wireless Personal Area Network) are characterized by low computation, memory and storage space, and they do not possess an infrastructure. This makes them dynamic... more
IEEE 802.15.4-based devices networks known by the name of LR-WPAN (Low Rate Wireless Personal Area Network) are characterized by low computation, memory and storage space, and they do not possess an infrastructure. This makes them dynamic and easy to deploy, but in the other hand, this makes them very vulnerable to security issues, as they are low energy so they cant implement current security solutions, and they are deployed in non-secure environments that makes them susceptible to eavesdropping attacks. Most proposed solutions draw out the security of the bootstrapping and commissioning phases as the percentage of existing of an intruder in this time is very low. In this paper, we propose a security model for LR-WPANs based on symmetric cryptography, which takes into account securing the bootstrapping phase, with an analysis of the effectiveness of this proposal and the measures of its implementation.
Research Interests:
Mobile Ad Hoc network (MANET) is a collection of smart mobile nodes, which form a dynamic and autonomous system. Since mobile nodes are free to move, they cause frequent changes in network topology and decrease the overall network... more
Mobile Ad Hoc network (MANET) is a collection of smart mobile nodes, which form a dynamic and autonomous system. Since mobile nodes are free to move, they cause frequent changes in network topology and decrease the overall network performances. Therefore, the task of finding and maintaining a reliable route constitute the main issue in the design of efficient routing protocol for MANET. In this paper, we introduce a novel Mobility Adaptive AODV routing protocol (MA-AODV), which uses the degree of mobility time variation and the local route repair approach to mitigate the influence of high mobility and improve routing performances. We implemented the MA-AODV on network simulator NS2. Then, we evaluated the performance of MA-AODV and AODV based on node mobility variation such as speed and pause time. The comparison of performance metrics, such as Packet delivery Ratio, Throughput, routing overhead and communication delay demonstrates that MA-AODV outperforms AODV in high mobility envi...
In this paper, we propose a deep learning framework for malware classification. There was a big boom within the quantity of malware in current years which poses an extreme safety chance to financial establishments, agencies, and people.... more
In this paper, we propose a deep learning framework for malware classification. There was a big boom within the quantity of malware in current years which poses an extreme safety chance to financial establishments, agencies, and people. In order to fight the proliferation of malware, new techniques are essential to quickly perceive and classify malware samples so that their behavior can be analyzed. Machine learning methods are becoming famous for classifying malware, but, the maximum of the modern gadget gaining knowledge of strategies for malware classification use machine learning algorithms (e.g., SVM). Currently, Convolutional Neural Networks (CNN), a deep getting to know approach, have proven advanced performance in comparison to traditional getting to know algorithms, particularly in duties which include image classification. Influenced by way of this achievement, we recommend a CNN-based architecture to classify malware samples. We convert malware binaries to a grayscale ima...
Research Interests:
Objective: Newborn malware increase significantly in recent years, becoming more dangerous for many applications. So, researchers are focusing more on solutions that serve the defense of new malwares trends and variance, especially... more
Objective: Newborn malware increase significantly in recent years, becoming more dangerous for many applications. So, researchers are focusing more on solutions that serve the defense of new malwares trends and variance, especially zero-day malware attacks. The prime goal of our proposition is to reach a high security level by defending against malware attacks effectively using advanced techniques. Methods: In this paper, we propose an Intelligent Cybersecurity Framework specialized on malware attacks in a layered architecture. After receiving the unknown malware, the Framework Core layer use malware visualization technique to process unknown samples of the malicious software. Then, we classify malware samples into their families using: K-Nearest Neighbor, Decision Tree and Random Forest algorithms. Classification results are given in the last layer, and based on a Malware Behavior Database we are able to warn users by giving them a detail report on the malicious behavior of the giv...
Ad Hoc Networks provide a real opportunity to design flexible networks, very simple to deploy. However they remain a particular computation environment, characterized by the deficiency of pre-existed and centralized infrastructure. In the... more
Ad Hoc Networks provide a real opportunity to design flexible networks, very simple to deploy. However they remain a particular computation environment, characterized by the deficiency of pre-existed and centralized infrastructure. In the other hand, SIP protocol, which knows a huge booming in internet networks, requires centralized entities, like proxy server, registrar server and location service; consequently SIP is not adapted to Ad Hoc networks. In this paper, we present and evaluate a new technique, which we have called Virtual Network for SIP (VNSIP) to fix the problem related to the constraints of SIP deployment in Ad Hoc network. The main idea of this technique is to create a virtual infrastructure, enabling SIP to proceed in a distributed architecture inside the Ad hoc Network.
Research Interests:
With the revolution that the education field has known concerning the methods of learning and especially the integration of new technology, several new tools have appeared to replace the tools already existing, and among them there are... more
With the revolution that the education field has known concerning the methods of learning and especially the integration of new technology, several new tools have appeared to replace the tools already existing, and among them there are serious games, serious games as new tool dedicated to education have occupied an important place, and replaced other tools often used in the learning process. But in the order that serious games reach the intended objectives and help instructors to achieve their perspectives considered, they must be equipped with a guidance and assistance system that will assist the learners during the progression in the sequence of the video game, and in addition, they must be equipped with a system of learning analytics that will help instructors to improve the learning process and teaching methods according to the learning outcomes and feedbacks of their learners. In this perspective of research and development we will establish in this paper a new system of assist...
Research Interests:
Research Interests:
The Cloud E-Learning Systems for the Arabic language are relevant environments in many areas of training (teaching Arabic language) but also pose problems related to their creation tedious, costly in resources and time, and problems... more
The Cloud E-Learning Systems for the Arabic language are relevant environments in many areas of training (teaching Arabic language) but also pose problems related to their creation tedious, costly in resources and time, and problems related to the search for information because of the increasing amount of information available and because of the methods of indexing, which is based on static methods such as keyword search that makes irrelevant the research process. For this, a new method of indexation is required. In this paper, a new Arabic text is proposed indexing approach using the creation of a new application profile of the LOM metadata schema (Learning Object Metadata) for the Arabic language. This profile includes the fields of LOM standard, and adds new fields for specific search information to Arabic language, and meets the needs of a teacher. Also, it's all using natural language processing tools like SAPA and AL-KHALIL.
Research Interests:
Research Interests:
... European Journal of Scientific Research 32 (2009) 151-157. Design of new multi standard patch antenna GSM/PCS/UMTS/HIPERLAN for mobile cellular phones. M. Ben Ahmed, M. Bouhorma, F. Elouaai, A. Mamouni 1. (2009). ...