The application of artificial intelligence to domain-specific textual analysis has opened new possibilities in natural language processing, particularly in the context of fatwas-authoritative Islamic legal opinions. This study presents a comparative evaluation of three language embedding models-Sentence Transformers, AraBERTv2, and MARBERT-within a Retrieval-Augmented Generation (RAG) framework powered by the Gemini model. A curated corpus of 285 texts, comprising fatwas, Qur’anic exegesis, and related jurisprudential writings, serves as the basis for evaluating semantic comprehension, retrieval accuracy, and generative performance. The findings demonstrate the superior performance of Arabic-specific models, with MARBERT and AraBERTv2 notably outperforming the multilingual Sentence Transformers in capturing the nuanced language and legal reasoning typical of fatwas. These results highlight the significance of culturally and linguistically specialized models in processing religious legal discourse.

This paper introduces AHARP (Adaptive Hybrid Agent-based Routing Protocol), a novel routing protocol designed for the Internet of Vehicles (IoV). AHARP integrates reactive, proactive, and context-aware routing strategies with an enhanced dynamic clustering mechanism to address the challenges of high mobility, frequent topology changes, and resource constraints in vehicular networks. The protocol dynamically groups vehicles based on their geographic proximity, speed, and road type, ensuring efficient cluster formation and management. Extensive simulations demonstrate that AHARP significantly outperforms existing protocols in terms of packet delivery ratio (PDR), end-to-end delay, and location service efficiency. By reducing control message overhead, improving route discovery efficiency, and adapting to dynamic network conditions in real-time, AHARP provides a robust and scalable solution for high-mobility environments.

Faced with multiple societal challenges, the healthcare sector has been compelled to leverage recent and emerging technologies to adapt. Blockchain is one of the leading technologies, offering transparency, process automation, immutability of traces and the ability to scale up in terms of both the volume of processes and the number of players interacting. The goal of the paper is to show the potential of blockchain technology - alone or merged with other technologies - to help the healthcare system evolve and provide scalable, efficient and secure solutions to four healthcare applications: electronic health record (EHR) storage, health data sharing, remote patient monitoring, and pharmaceutical supply chains. After identifying the functional and security requirements of healthcare systems, the paper conducts an in-depth review of the literature. The survey assesses the effectiveness of blockchain-based solutions in meeting functional, privacy and security needs. It is completed by an analysis of the synergies that can be expected between blockchain and emerging technologies, e.g. artificial intelligence, federated learning, the Internet of Things (IoT), and Large Language Models (LLM), to the benefit of security or privacy in healthcare.

Data Monitoring becomes mandatory for several IoT applications including smart greenhouse. It aims to increase the quality of information by identifying existing errors and anomalies, especially using outlier detection process by machine learning-data classification. Existing approaches require the knowledge of data characteristics in advance. However, this requirement is not always possible in IoT due to the heterogeneity of devices. Therefore, this paper provides VoteIoT: a new monitoring method based on data analytic and vote clustering outcome. In this way, we increase the probability of making a good decision and guaranteeing a good harvest of greenhouses. To evaluate the proposed solution, we used a real database extended by augmented data. The results show a good response time, below 0.01 seconds, as well as a good detection accuracy of 97%. Additionally, the false alarms are below 3% and therefore, a low useful data loss. Moreover, we have managed to increase the probability of a good decision compared to existing solutions.

Summary The reliability and latency requirements of wireless sensor network‐based smart grid communications are met in large part by MAC protocols. Developed by IEEE, time slotted channel hopping (TSCH), a method that is effective, dependable, and predictable. However, the TSCH standard does not enable mobility and does not offer any solution for scheduling, especially in IEEE 802.15.4 TSCH, the most recent generation of extremely dependable and low‐power MAC protocols. Recently, MSU‐TSCH a time‐frequency communication schedule was proposed to provide mobility to TSCH. Despite its distinctive qualities, MSU‐TSCH has the drawback of computing the TSCH schedule at each node independently of its traffic load, which can significantly increase the communication delay. Due to this limitation, MSU‐TSCH is not suitable for some delay‐sensitive smart grid applications. In this article, we provide an improved MSU‐TSCH‐based TSCH protocol, called Mobility‐TSCH, that dynamically adjusts time slot assignments based on traffic volume and latency requirement. Moreover, the protocol Mobility‐TSCH adapts to topology changes and supports mobility. Additionally, it optimizes time slot allocation by prioritizing nodes closest to the sink. The performance and evaluation analysis of Mobility‐TSCH compared to the original MSU‐TSCH, reveal that the communication delay is greatly reduced, decreases the average end‐to‐end latency, the high packet delivery ratio (PDR), Increase the performance of both metrics, parent connectivity ratio (PCR) and convergence time (CT), while maintaining a minimal overhead signaling.

The rise of cyberattacks has necessitated the development of effective malware detection mechanisms. Deep learning, with its ability to learn complex features from raw data, has been widely used for this purpose. This paper presents a two-fold contribution to the field of malware detection using deep learning. Firstly, we use seven pretrained CNN models to classify malware images from the Malimg dataset. While these models achieved high accuracy, they presents low precision and F1-score, indicating that they were prone to false positives and false negatives. Additionally, these pre-trained models are susceptible to overfitting, which is a common issue with transfer learning. To overcome this limitation, we propose a custom CNN model consisting of six layers, trained from scratch on the Malimg dataset. To address potential issues like over-fitting and data imbalance when training models from scratch, we used regularization techniques such as L1 or L2 regularization, dropout. Our proposed custom CNN model outperformed the pretrained models, achieving best/average accuracy values over 5 trials of 100%/98.26%. We also found that our custom model was less susceptible to over-fitting and adversarial attacks. Our proposed approach provides a promising solution to the problem of limitations in using pre-trained models for malware detection.

The rapid proliferation of the Internet of Things (IoT) has led to the interconnection of billions of intelligent sensors. However, this interconnection has also introduced significant security challenges. Recently, deep learning has shown promising results in several fields including attacks detection. This paper aims to improve IoT security through the application of deep learning techniques. Specifically, we chose the Convolutional Neural Network as a means to identify and counteract the most severe IoT attacks, such as denial-of-service (DOS) and distributed denial-of-service (DDoS) attacks. The experimental results demonstrate that our CNN is highly effective in identifying DDOS and DOS attacks in the real dataset Bot-IoT, achieving an accuracy rate of 99.920%.

On top of the low-power IEEE 802.15.4 radio, IEEE created IEEE 802.15.4e time slotted channel hopping (TSCH), an exceptionally efficient, reliable, and predictable time-frequency-enabled medium access control protocol for the industrial sector. However, the IEEE 802.15.4e TSCH specification does not address how scheduling would be created, updated, or maintained. Moreover, TSCH does not support mobility. Although several scheduling techniques have been proposed in the literature to fill this gap, these techniques did not consider networking metrics, such as duty cycle, network capacity, end-to-end delay, and packet delivery ratio. In this article, we develop a new dynamic scheduling approach for TSCH that supports mobility and adapts to topology changes, called mobile scheduling updated TSCH (MSU-TSCH), that attempts to schedule time slots by first picking the closest nodes to the sink. We undertake comprehensive simulations to assess the effectiveness of MSU-TSCH with PRuning-based coloring scheduling, an existing scheduling algorithm in a mobile context. On the one hand, this proposal reduces the received energy consumption by up to 40%. On the other hand, it decreases the average end-to-end latency by 30%.

Technologies dedicated radio infrastructure deployments are no longer adequate to ensure large-scale, low-cost, and reliable communications with the growing adoption of scattered wireless technologies for current services. The goal of this article is to allow the deployment of a radio network infrastructure for numerous client applications, hence building the Internet of Things (IoT), IEEE established IEEE 802.15.4e time slotted channel hopping (TSCH), an extremely efficient, reliable, and predictable time-frequency enabled medium access control (MAC) protocol for the industrial sector, on top of the low-power IEEE 802.15.4 radio. A MAC communication schedule may be constructed from an IEEE 802.15.4e TSCH communication schedule. The IEEE 802.15.4e TSCH definition, on the other hand, makes no mention of how such scheduling may be generated, modified, or maintained. It also has no jurisdiction over the unit in charge of these obligations. This means that the standard is missing the required scheduling mechanism. To meet this demand, several communication scheduling approaches have been presented in the literature. We first establish a novel decentralized communication scheduling approach called mobile scheduling updated TSCH (MSU-TSCH), which implies that network traffic can move in any direction rather than from leave nodes to the root, in this study. The MSU-TSCH algorithm tries to plan time slots by selecting the node that is nearest to the user. While selecting a nearby node, it seeks to assign a roughly equal quantity of dedicated time slots to each member node (or member neighbor). Other scheduling algorithms may not be able to construct better schedules with neighbor nodes as a consequence.

A blockchain is a distributed and decentralized database that allows users to securely store and exchange data without requiring the intervention of a third party. Information, called transactions, is collected in blocks, which are then linked together via cryptographic processes in an irreversible way. The registry has served as a historical record of all actions taken by participants in the network since its launch. An increase in the number of transactions, leading to a considerable increase in the size of the primary blockchains, making them more difficult to maintain, perhaps discouraging certain nodes from storing the entire blockchain and therefore weakening decentralization. In this study, we introduce the low-storage node, a new type of node that stores chunks of blocks rather than whole blocks and is encoded with an erasure code. A low-storage node recovers the initial block by downloading and decoding a enough encoded fragments from other nodes in the network. This strategy has the advantage of allowing certain nodes to keep a reduced version of the blockchain while contributing to its decentralization. This simplifies the scaling of blockchains, which is one of the main flaws of the technology. BlockStock is a complete system that allows nodes to rent out its additional storage space to others. The main innovation is the use of blockchain-based smart contracts that enable frequent, automated and secure payments based on proofs of recovery provided by storage servers.

The 15thIEEE International Conference on Security of Information and Networks (SIN 2022) was held in Sousse, Tunisia and mutually organized by University of Sfax in Tunisia and Hasan Kalyoncu University in Turkey.

The Industrial Internet of Things (IIo$T$) is rapidly growing in tandem with security concerns. In this paper, we propose two deep learning models for classifying IIo$T$traffic in binary and multi-class contexts in order to detect intrusions in IIoT networks. To train the models, a recent public dataset is used. The results are very encouraging, with accuracy more than 99%.

Internet network carries a huge stream of HTTP requests and responses between users and servers. Securing server data access is primordial for internet users to enhance confidence in electronic services. Therefore, it is essential to detect and stop malicious HTTP requests arriving on the server quickly and with high accuracy. This paper presents a smart web application firewall (SWAF) based on a convolutional neural network. Using 5-fold cross-validation method, we trained and tested our proposed web application firewall with the CSIC dataset. Our SWAF achieves a high attacks detection rate. It can catch and stop a malicious HTTP request in 2.3ms with an accuracy rate of 99.1%.

Federated Learning (FL) is a feasible technology to collaboratively train a model without sharing private data. This approach differs from traditional machine learning techniques, which aggregate local datasets in a single server. Thus, FL is adopted in the Healthcare sector to preserve the privacy of collected sensitive medical data from heterogenous and resource-constrained Internet of Medical Things (IoMT). However, FL requires aggregating all trained local models in a central server that presents a single point of failure. To address this issue, we propose a novel Blockchain-based Federated Learning architecture, which is applied to detect malicious network traffic in IoMT environments. In this paper, the proposed architecture takes advantage of a Hyperledger Fabric channel coupled with FL to manage efficiently and securely the learning process of an Intrusion Detection System (IDS). The Blockchain channel replaces the commonly used central server with the traditional FL approach. Moreover, the proposed approach benefits from the inherent features of Blockchain and FL. Besides, it secures patient data collection from the IoMT by examining the network traffic for unauthorised behaviour or policy breaches.

Abstract Blockchain is a database that contains the history of all exchanges made between its users since its creation. Blockchain is a new tool that enables essential distributed applications without the need for centralized trust. It is a transparent and secure technology for storing and transmitting information that operates without a central control body. Moreover, the large‐scale presence of wireless sensors, especially in the IoT, produce a large volume of data. This data must be protected to guarantee its correctness. However, due to the difficulty of encrypting this data, there are many problems, including limited resources, whether in terms of computation, memory, or energy, as well as the complexity of encryption algorithms. Therefore, we wanted, through this article, to show the importance of adopting the blockchain in wireless sensors. This enables it to send data as quickly and securely as possible, as little of the literature has dealt with this topic. For this, one imaginable solution must be managed in WSN which is to put the necessary keys for networks or groups at the level of each sensor for the different scenarios implemented, mobile node and orphan nodes, so that the latter can authenticate and link to these multiple networks or clusters, using our blockchain security IoT (BSI) protocol. The latter makes it possible to design a decentralized, transparent, and scalable authentication system, which does not negatively impact the performance of sensors or that of networks. This system must provide complete freedom to change the state of the sensor from one network to another, while ensuring the safety of the latter. This means that if a sensor is authenticated in a legitimate network, it becomes reliable and accepted by all other networks. This allows you to have a global vision on all networks. We evaluate the performance of our protocol with simulations using MATLAB. The results confirm that the BSI protocol is robust and efficient, provides lower power consumption and fast computing time.

Abstract Information hiding aims to embed a crucial amount of confidential data records into the multimedia, such as text, audio, static and dynamic image, and video. Image‐based information hiding has been a significantly important topic for digital forensics. Here, active image deep steganographic approaches have come forward for hiding data. The least significant bit (LSB) steganography approach is proposed to conceal a secret message into the original image. First, the lightweight stream encryption cryptography encrypts secret information in the cover image to protect embedded information from source to destination. Whereas the encrypted embedded cover information into the carrier of stego‐image with the help of the LSB and then transmit. In the proposed investigational scheme, a convolutional neural net is used. A model is trained to detect and extract patterns of image hidden features, encrypted stego‐image optimization, and classify original and cover images of steganography. Through the experiment result on the forensic image database for mobile steganography of the Center for Statistics and Application in Forensic Evidence, the overall embedded and extracting that the proposed scheme can achieve information hiding as well as revealing with an accuracy rate of 95.1%. The experimental result shows the robustness of the model in terms of efficiency as compared to other state‐of‐the‐art schemes.

In the transmission of medical images, if the image is not processed, it is very likely to leak data and personal privacy, resulting in unpredictable consequences. Traditional encryption algorithms have limited ability to deal with complex data. The chaotic system is characterized by randomness and ergodicity, which has advantages over traditional encryption algorithms in image encryption processing. A novel V-net convolutional neural network (CNN) based on four-dimensional hyperchaotic system for medical image encryption is presented in this study. Firstly, the plaintext medical images are processed into 4D hyperchaotic sequence images, including image segmentation, chaotic system processing, and pseudorandom sequence generation. Then, V-net CNN is used to train chaotic sequences to eliminate the periodicity of chaotic sequences. Finally, the chaotic sequence image is diffused to change the raw image pixel to realize the encryption processing. Simulation test analysis demonstrates that the proposed algorithm has better effect, robustness, and plaintext sensitivity.

A blockchain is a database that contains the history of all exchanges made between its users since its creation. A blockchain is a distributed and secure ledger of all transactions made since the start of the distributed system. It is a technology for storing and transmitting information, transparent, secure, and operating without a central control body. Our paper studies a new device authentication for mobile sensor node to prove its authenticity to unknown network manager. To solve the authentication of sensor among multiple networks, our proposal a blockchain scheme where the transaction specifies the authentication of given cluster head CH. As we claim, a blockchain guarantees an integrity and availability of message under assumption that every node has some public and private key pairs. However, it does not provide any authentication mechanism for symmetric key. Hence, the proposed scheme is secure as we claim. More concretely, in the protocol proposed Blockchain Security IoT (BSI) is to provide authentication between the mobile base station (BS), the cluster head and the member nodes for wireless sensor networks (WSN). Our protocol BSI protocol makes it possible to put the necessary keys of the networks at the level of each sensor for the different scenarios carried out, BS mobile node and migration node. We evaluate the performance of our protocol with simulations using MATLAB. The results confirm that the BSI protocol is robust and efficient, provides lower power consumption and fast computing time.

Our paper proposes a new device authentication scheme for mobile sensor node called Mobile Data Collector (MDC). Moreover, to validate the data brought by the MDC to the base station (BS), we validate it and then store it. To solve MDC authentication between multiple devices, we proposed blockchain scheme to provide more ease, communication and security between different devices. For this to happen, the last MDC authentication (meaning the first time the information is gathered) is performed by the CH'S first encounter with the classic authentication, and here the protocol accepts or rejects the MDC. Once the CH has authenticated the MDC, CH sends a transaction to the blockchain to verify the legality of the MDC access. Then, when the MDC requests the collected data from another CH in the network, at this point, any CH verifies the trust of the MDC by communicating with the blockchain. Hence, the proposed scheme is as safe as we claim. More specifically, in the proposed protocol for Blockchain Security IoT (Block_MDC) is to provide authentication between the Mobile Data Set (MDC), the head of the group and the member nodes of the WSN. We evaluate the performance of our protocol using simulations using MATLAB. The results confirm that the Block_MDC protocol is robust, efficient, and offers lower power consumption and fast computing time.

With the emergence of cloud robotics, computation offloading presents a new trend in cloud computing that has been applied to robots; to provide them with resources for performing computationally intensive tasks. In most scientific research, the main objectives behind computation offloading are reducing energy consumption and minimizing the execution time of robotics applications. However, these two metrics are conflicting, and optimizing them simultaneously is challenging. Reducing energy consumption may lead to a rise in the completion time, and vice-versa. In this paper, we consider the problem of optimization of energy consumption and completion time in a cloud robotic system. We formulated the offloading decision as a multi-objective optimization problem. We further adapted the Non-dominated Sorting Genetic Algorithm (NSGA-II) to find a set of Paretooptimal solutions. Through simulations, we demonstrated that our offloading solution can save 80% of the robot’s energy consumption; and reduce 70% of the application completion time. We proved also the adaptability of the model against bandwidth changes.

Remote Patient Monitoring (RPM) is a form of telehealth or virtual health that strengthens online medical services and allows delivering healthcare remotely. Nowadays, remote patient monitoring systems (RPMS) are widely used by healthcare providers to remotely monitor the vital signs of patients. As the RPM field expands, concerns about efficient and secure medical data transmission are raised. This kind of patient medical data is collected by the mean of Internet of Healthcare Things (IoHT) or sometimes denoted as Internet of Medical Things (IoMT) devices. The collected data needs to be stored and retrieved with highly assured levels of security and privacy as the data comprises private and critical patients’ information. To secure medical data, this paper proposes a blockchain-based architecture to manage access control to medical data and to preserve patient’s data privacy. The blockchain-based system is built on Hyperledger Fabric, a permissioned distributed ledger solution, and the ledgers and transactions are stored in the cloud. The proposed architecture is designed to contribute to the robustness of the RPM systems and to avoid recorded security limitations in commonly used permissioned blockchains methods. Performance evaluation has proved the robustness and superiority of the proposed system in terms of data confidentiality, integrity, availability, traceability, scalability, and data privacy while integrated with the RPM services.

Authentication is the primary and mandatory process for any Information and Communication Technology (ICT) application to prove the legitimacy of the genuine user. It becomes more important and crucial for public platforms like e-governance platforms. The Government of India is transforming the country into Digital India through various e-governance initiatives based on ICT. For authentication, National e-Authentication Framework (NeAF) was proposed by the Indian government which is a policy framework for authentication. This framework does not provide any technical and unified solution for authentication systems while it is based on centralized verification data. In this paper, we proposed a solution for the authentication which provides the unified authentication solution for the Indian e-governance system with existing infrastructure. This solution also provides the features such as scalability, security, and transparency based on distributed computing and working on multiserver architecture. This solution also fulfills the need of the current Indian government to provide multiple e-governance services through a single smart card.

The adoption of Internet of Things (IoT) technology across many applications, such as autonomous systems, communication, and healthcare, is driving the market’s growth at a positive rate. The emergence of advanced data analytics techniques such as blockchain for connected IoT devices has the potential to reduce the cost and increase in cloud platform adoption. Blockchain is a key technology for real-time IoT applications providing trust in distributed robotic systems running on embedded hardware without the need for certification authorities. There are many challenges in blockchain IoT applications such as the power consumption and the execution time. These specific constraints have to be carefully considered besides other constraints such as number of nodes and data security. In this paper, a novel approach is discussed based on hybrid HW/SW architecture and designed for Proof of Work (PoW) consensus which is the most used consensus mechanism in blockchain. The proposed architecture is validated using the Ethereum blockchain with the Keccak 256 and the field-programmable gate array (FPGA) ZedBoard development kit. This implementation shows improvement in execution time of 338% and minimizing power consumption of 255% compared to the use of Nvidia Maxwell GPUs.

The rise of large-scale wireless sensor networks (LSWSNs), containing thousands of sensor nodes (SNs) that spread over large geographic areas, necessitates new Quality of Service (QoS) efficient data collection techniques. Data collection and transmission in LSWSNs are considered the most challenging issues. This study presents a new hybrid protocol called MDC-K that is a combination of the K-means machine learning clustering algorithm and mobile data collector (MDC) to improve the QoS criteria of clustering protocols for LSWSNs. It is based on a new routing model using the clustering approach for LSWSNs. These protocols have the capability to adopt methods that are appropriate for clustering and routing with the best value of QoS criteria. Specifically, the proposed protocol called MDC-K uses machine learning K-means clustering algorithm to reduce energy consumption in cluster head (CH) election phase and to improve the election of CH. In addition, a mobile data collector (MDC) is used as an intermediate between the CH and the base station (BS) to further enhance the QoS criteria of WSN, to minimize time delays during data collection, and to improve the transmission phase of clustering protocol. The obtained simulation results demonstrate that MDC-K improves the energy consumption and QoS metrics compared to LEACH, LEACH-K, MDC maximum residual energy leach, and TEEN protocols.

Software-defined networking is an evolving network architecture beheading the traditional network architecture focusing its disadvantages in a limited perspective. A couple of decades before, programming and networking were viewed as different domains which today with the lights of SDN bridging themselves together. This is to overcome the existing challenges faced by the networking domain and an attempt to propose cost-efficient effective and feasible solutions. Changes to the existing network architecture are inevitable considering the volume of connected devices and the data being held together. SDN introduces a decoupled architecture and brings customization within the network making it easy to configure, manage, and troubleshoot. This paper focuses on the evolving network architecture, the software-defined networking. Unlike a generic view on the evolving network, which makes work as a review, this work addresses various perspectives of the architecture leaving it an intermediate work in between the review of the literature and implementation, contributing towards factors like the design, programmability, security, security behaviors, and security lapses. This paper also analyses various weak points of the architecture and evolves the attack vectors in each plane leaving a conclusion to further progress towards identifying the impacts of the attacks and proposing mitigation strategies.

Volunteer computing based data processing is a new trend in healthcare applications. Researchers are now leveraging volunteer computing power to train deep learning networks consisting of billions of parameters. Breast cancer is the second most common cause of death in women among cancers. The early detection of cancer may diminish the death risk of patients. Since the diagnosis of breast cancer manually takes lengthy time and there is a scarcity of detection systems, development of an automatic diagnosis system is needed for early detection of cancer. Machine learning models are now widely used for cancer detection and prediction research for improving the successive therapy of patients. Considering this need, this study implements pre-trained convolutional neural network based models for detecting breast cancer using ultrasound images. In particular, we tuned the pre-trained models for extracting key features from ultrasound images and included a classifier on the top layer. We measured accuracy of seven popular state-of-the-art pre-trained models using different optimizers and hyper-parameters through fivefold cross validation. Moreover, we consider Grad-CAM and occlusion mapping techniques to examine how well the models extract key features from the ultrasound images to detect cancers. We observe that after fine tuning, DenseNet201 and ResNet50 show 100% accuracy with Adam and RMSprop optimizers. VGG16 shows 100% accuracy using the Stochastic Gradient Descent optimizer. We also develop a custom convolutional neural network model with a smaller number of layers compared to large layers in the pre-trained models. The model also shows 100% accuracy using the Adam optimizer in classifying healthy and breast cancer patients. It is our belief that the model will assist healthcare experts with improved and faster patient screening and pave a way to further breast cancer research.

Multicontroller software‐defined networks have been widely adopted to enable management of large‐scale networks. However, they are vulnerable to several attacks including false data injection, which creates topology inconsistency among controllers. To deal with this issue, we propose BMC‐SDN, a security architecture that integrates blockchain and multicontroller SDN and divides the network into several domains. Each SDN domain is managed by one master controller that communicates through blockchain with the masters of the other domains. The master controller creates blocks of network flow updates, and its redundant controllers validate the new block based on a proposed reputation mechanism. The reputation mechanism rates the controllers, i.e., block creator and voters, after each voting operation using constant and combined adaptive fading reputation strategies. The evaluation results demonstrate a fast and optimal detection of fraudulent flow rule injection.

Http requests refer to the way web clients can communicate with web servers. Web attacks represent suspicious changes to normal web requests. It is important to perform detection quickly and accurately for the efficient operation of highly solicited web servers. In this paper, we propose a Memory Convolutional Neural Network “M-CNN” for effectively modeling the information contained in the request data. We also provide a method for automatically extracting robust features from raw data. Experimental results demonstrate that our M-CNN model can extract more complex features by combining a convolutional neural network (CNN) and long short-term memory (LSTM). The CNN layer is used to clean the request from useless information, the LSTM layer is suitable for modeling time information. Our proposed M-CNN model can easily detect the sequence of requests sent by a web-attacker, which is difficult to identify by the state-of-the-art techniques. Finally, the proposed M-CNN model outperforms other state-of-the-art machine learning techniques on the CSIC dataset, achieving an overall accuracy of 99.258%.

Cybersecurity attacks are exponentially increasing, making existing detection mechanisms insufficient and enhancing the necessity to design more relevant prediction models and approaches. This issue is still an open research problem since existing attack prediction models are failing to follow the huge amount of attacks and their variety. Recently, machine learning approaches and especially deep learning techniques have received much attention from researchers since their unparalleled high performance in several prediction-based fields. In this context, this paper explores the application of deep learning techniques for predicting cybersecurity attacks. Particularly, it proposes a new LSTM (Long Short-Term Memory), RNN (Recurrent Neural Network), and MLP (Multilayer Perceptron) based models carefully designed to predict the type of attack potentially to hap-pen. The proposed models were validated using a recently available dataset called CTF showing encouraging results especially for the LSTM model with an f-measure greater than 93%.

Malaria is a contagious disease that affects millions of lives every year. Traditional diagnosis of malaria in laboratory requires an experienced person and careful inspection to discriminate healthy and infected red blood cells (RBCs). It is also very time-consuming and may produce inaccurate reports due to human errors. Cognitive computing and deep learning algorithms simulate human intelligence to make better human decisions in applications like sentiment analysis, speech recognition, face detection, disease detection, and prediction. Due to the advancement of cognitive computing and machine learning techniques, they are now widely used to detect and predict early disease symptoms in healthcare field. With the early prediction results, healthcare professionals can provide better decisions for patient diagnosis and treatment. Machine learning algorithms also aid the humans to process huge and complex medical datasets and then analyze them into clinical insights. This paper looks for leveraging deep learning algorithms for detecting a deadly disease, malaria, for mobile healthcare solution of patients building an effective mobile system. The objective of this paper is to show how deep learning architecture such as convolutional neural network (CNN) which can be useful in real-time malaria detection effectively and accurately from input images and to reduce manual labor with a mobile application. To this end, we evaluate the performance of a custom CNN model using a cyclical stochastic gradient descent (SGD) optimizer with an automatic learning rate finder and obtain an accuracy of 97.30% in classifying healthy and infected cell images with a high degree of precision and sensitivity. This outcome of the paper will facilitate microscopy diagnosis of malaria to a mobile application so that reliability of the treatment and lack of medical expertise can be solved.

The emergence of cognitive computing and big data analytics revolutionize the healthcare domain, more specifically in detecting cancer. Lung cancer is one of the major reasons for death worldwide. The pulmonary nodules in the lung can be cancerous after development. Early detection of the pulmonary nodules can lead to early treatment and a significant reduction of death. In this paper, we proposed an end-to-end convolutional neural network- (CNN-) based automatic pulmonary nodule detection and classification system. The proposed CNN architecture has only four convolutional layers and is, therefore, light in nature. Each convolutional layer consists of two consecutive convolutional blocks, a connector convolutional block, nonlinear activation functions after each block, and a pooling block. The experiments are carried out using the Lung Image Database Consortium (LIDC) database. From the LIDC database, 1279 sample images are selected of which 569 are noncancerous, 278 are benign, and the rest are malignant. The proposed system achieved 97.9% accuracy. Compared to other famous CNN architecture, the proposed architecture has much lesser flops and parameters and is thereby suitable for real-time medical image analysis.

The MAVLink is a lightweight communication protocol between Unmanned Aerial Vehicles (UAVs) and ground control stations (GCSs). It defines a set of bi-directional messages exchanged between a UAV (aka drone) and a ground station. The messages carry out information about the UAV's states and control commands sent from the ground station. However, the MAVLink protocol is not secure and has several vulnerabilities to different attacks that result in critical threats and safety concerns. Very few studies provided solutions to this problem. In this paper, we discuss the security vulnerabilities of the MAVLink protocol and propose MAVSec, a security-integrated mechanism for MAVLink that leverages the use of encryption algorithms to ensure the protection of exchanged MAVLink messages between UAVs and GCSs. To validate MAVSec, we implemented it in Ardupilot and evaluated the performance of different encryption algorithms (i.e. AES-CBC, AES-CTR, RC4 and ChaCha20) in terms of memory usage and CPU consumption. The experimental results show that ChaCha20 has a better performance and is more efficient than other encryption algorithms. Integrating ChaCha20 into MAVLink can guarantee its messages confidentiality, without affecting its performance, while occupying less memory and CPU consumption, thus, preserving memory and saving the battery for the resource-constrained drone.

Cloud robotics is incessantly gaining ground, especially with the rapid expansion of wireless networks and Internet resources. In particular, computation offloading is emerging as a new trend, enabling robots with more powerful computation resources. It helps them to overcome the hardware and software limitations by leveraging parallel computing capabilities and the availability of large amounts of resources in the cloud. However, the performance gain of computation offloading in cloud robotics is still an ongoing research problem because of the conflicting factors that affect the performance. In this paper, we investigate this issue and we design a distributed cloud robotic architecture for computation offloading based on Kafka middleware as messaging broker. We experimentally validated our solution and tested its performance using image processing algorithms. Experimental results show a significant reduction in robot CPU load, as expected, with an increase in robot communication delays.

Several IoT applications are tightly dependent on the locations of the devices. However, localization algorithms can be easily compromised by injecting false locations. In this paper, we propose a Blockchain-based secure localization algorithm for the Internet of Things (IoT). The algorithm uses a public ledger (Blockchain) that contains nodes position and the list of their neighbor nodes. This ledger is shared among the IoT devices. Once an IoT device is localized its new position and the list of neighbor nodes are added to the Blockchain. This shared localization data will be used later by other IoT devices for their localization process. To avoid the attack where a malicious node sends a fake position, the correctness of the claimed position are verified before adding it to the Blockchain. Moreover, data exchanged between nodes (IoT devices) are signed to guarantee their authenticity and integrity. The integration of these security mechanisms into the localization process permits to exclude false data and therefore reduces the localization error. The simulation results show that adding the proposed security mechanism improves the localization accuracy of the algorithm when running in the presence of malicious nodes.

Recently, using Wireless Sensors Networks has increased rapidly in different domains. This advance has provides many solutions in several everyday life fields. Nevertheless, many problems of security and especially energy consumption have emerged. Due to this reasons many works propose solutions to increase the level of security and especially secure group communications. The communication requires common group key for protection of control messages and data reports. The group key should be updated when a node is compromised or a node leaves the group or a new node joins the group to achieve forward and backward security. It is in this context that our works was oriented to propose a new authentication scheme to improve the rekeying message authentication. Experimental results using real platform TelosB motes with tinyos operating system validate the efficiency of our proposed solution.

User authentication in classical networks is deeply addressed, but few results are related to Wireless Sensor Networks (WSNs). In addition, the proposed schemes do not provide mutual authentication or session-key agreement between the server and the user. Therefore, we present in this paper a lightweight user authentication scheme adapted to WSNs that provides mutual authentication and session-key agreement. The proposed scheme allows a user equipped with mobile device (typically PDA) to authenticate himself before gaining access to the WSN. The scheme is executed at two sides; the client side which controls the user's mobile device and the server side represented by the coordinator of the WSN. A security analysis of the scheme is presented and it proves its resilience against classical types of attacks. The scheme is also implemented on real platform of sensor nodes. This implementation proves that our scheme is lightweight and rapid as it requires approximately only 1s to be fully executed. In addition, we have made a comparison between our scheme and the existing ones based on their security properties, and shown that our proposed scheme outperforms the existing ones in terms of confidentiality, integrity, mutual authentication and session key generation with a lightweight computation overhead.

In 2004, Das et al. proposed a ldquoDynamic ID-based Remote User Authentication Scheme using Smart Cardsrdquo. This scheme have the advantage that users can choose and change their password freely and the server does not maintain any verifier table, which avoid the risk of stolen/modifying this table. However, in 2005, Liao et al. demonstrated that Das et al.'s scheme suffers from guessing attacks, unilateral authentication and revealing of user password and propose improvements to prevent these shortcomings. However, in this paper, we demonstrate that Liao et al.'s scheme is not secure and it is vulnerable to stolen/lost smart card attack, impersonation (forgery) attack and password revealing attack. In fact, we prove that the scheme is equivalent to no password scheme. Then, we propose possible improvements to Liao et al.'s scheme. We demonstrate through comparison between the three schemes that the proposed one is more secure while maintaining the same computational overhead as Das et al.'s scheme.