Distributed Denial of Service (DDoS) attacks pose a persistent threat to network security, requiring timely and scalable mitigation strategies. In this paper, we propose a novel collaborative architecture that integrates a P4-programmable data plane with an SDN control plane to enable real-time DDoS detection and response. At the core of our approach is a split early-exit neural network that performs partial inference in the data plane using a quantized Convolutional Neural Network (CNN), while deferring uncertain cases to a Gated Recurrent Unit (GRU) module in the control plane. This design enables high-speed classification at line rate with the ability to escalate more complex flows for deeper analysis. Experimental evaluation using real-world DDoS datasets demonstrates that our approach achieves high detection accuracy with significantly reduced inference latency and control plane overhead. These results highlight the potential of tightly coupled ML-P4-SDN systems for efficient, adaptive, and low-latency DDoS defense.

The Internet of Things (IoT) has become increasingly susceptible to cyber attacks, making it crucial to have strong detection mechanisms. This paper looks at using adversarial machine learning to boost IoT security. We implemented and evaluated Feedforward Neural Networks (FNN) and Long Short-Term Memory (LSTM) models on the Bot-IoT dataset for binary and multi-class classification tasks. We then evaluated how these models perform under Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) adversarial attacks. Our results show high accuracy in detecting attacks under normal conditions. However, the models showed major weaknesses when faced with adversarial examples. This study highlights the urgent need for building adversarially robust machine learning models for IoT security. It also gives insights into how different model architectures perform against various attack intensities.

Mobile tourism applications have gained massive popularity, offering various services such as booking accommodations, navigating unfamiliar locations, and providing travel recommendations. These applications have revolutionized travel planning, making it easier and more convenient for tourists in smart cities. This work aims to enhance the tourist appeal of Morocco’s historical regions by developing a mobile application called E-Tourism, which leverages computer vision technology for historical site recognition in smart cities. The proposed application provides detailed descriptions and historical context for various heritage sites. Moreover, it utilizes a pre-trained lightweight neural network model to accurately recognize and provide information about historical landmarks, even when GPS fails to pinpoint users’ locations precisely. Users can scan landmarks with their device’s camera, and the application will display relevant information, enriching their visit with an educational experience.

Software-defined networking (SDN) enables dynamic, flexible, and programmatically efficient network design by separating the control plane from the data plane, revolutionizing network control and management. In response to the demands of large data centers, SDNs facilitate resource provision, traffic management, and network reconfiguration, while enhancing network virtualization and security. However, SDNs are vulnerable to conventional security threats. This paper proposes a comprehensive three-step approach for assessing security risks in SDN environments. Our methodology incorporates Multi-Criteria Decision Making (MCDM) techniques as follows: (1) Initial threat identification using Hesitant Fuzzy Sets-TOPSIS (HFS-TOPSIS), (2) Risk quantification via Hesitant Fuzzy Analytical Hierarchical Process (HF-AHP), and (3) Mitigation planning through Fault Tree Analysis (FTA). This structured approach ensures a thorough risk assessment and effective mitigation, enabling network administrators to identify potential risks and implement appropriate remedies before deploying SDN architectures. Our approach is compared with traditional risk-scoring methods to demonstrate its superior performance.

Software-defined Networks (SDNs) offer flexibility and programmability but introduce new attack surfaces, especially at the edge. Man-in-the-Middle (MitM) attacks on the control channel between the controller and edge devices pose a significant threat. This paper proposes a lightweight approach for detecting MitM attacks in SDN-based edge architectures. We evaluate several machine learning classifiers based on their effectiveness and efficiency for resource-constrained edge environments. Our approach analyzes real-time network traffic based on features sensitive to MitM activities. Through a simulated case study, we compare the performance of a rule-based baseline against various classifiers, including Gaussian Naive Bayes, Logistic Regression, Decision Tree, Random Forest, LightGBM, and XGBoost. The results demonstrate that the Decision Tree classifier achieves excellent performance, with 99% accuracy, precision, and recall, and critically, exhibits one of the lowest detection latencies (0.7 ms). This balance of high detection capability and low computational overhead positions Decision Trees as a highly suitable lightweight solution for real-time MitM attack detection in SDN edge architectures, outperforming simpler methods like Gaussian Naive Bayes and the rule-based baseline, and offering a more efficient alternative compared to complex ensemble models when latency is a primary concern. We also analyze the relative CPU and memory consumption, further supporting the practicality of Decision Trees for edge deployment.

Software-Defined Networking (SDN) introduces flexibility by decoupling control and data planes. However, this separation exposes the data plane to new threats, particularly malicious data sharing between network nodes. Existing trust mechanisms are often inadequate or too resource-intensive for edge environments. This paper proposes a novel framework to enhance trust and detect malicious data sharing within the SDN data plane. The approach combines a dynamic trust model-based on Ability, Benevolence, and Integrity (ABI)-with a lightweight deep learning anomaly detection system leveraging Autoencoders (AEs) and Graph Neural Networks (GNNs). Designed for integration with P4-programmable switches, the framework enables real-time analysis and response directly at the data plane. Key contributions include: (1) a tailored ABI-based trust model for SDN data planes, (2) a lightweight distributed detection architecture using AEs/GNNs, and (3) a P4-based testbed design for validation. This work aims to significantly improve trust establishment, accurately detect malicious data sharing, and minimize resource overhead, paving the way for more secure and resilient SDN data planes. The results demonstrate 97 % accuracy in detecting anomalies and highlight the critical challenges of classifying compromised nodes under class imbalance.

In the realm of future smart system development, one domain poised for significant growth is the emergence of smart cities worldwide, which aim to enhance people's quality of life. In fact, a smart city is characterized by the integration of a large volume of data and wireless communication enabled services, encompassing automated healthcare, smart transportation, home automation, smart parking, and traffic management, among others. However, the rapid growth of smart cities presents challenges in ensuring secure and reliable exchange of information between IoT devices and entities within the smart city ecosystem due to the enormous amount of data traffic generated by intelligent information systems. To address these challenges, the deployment of blockchain technology within smart cities holds promise for improving data integrity and facilitating the transparent, reliable, secure, and equitable delivery of services and applications. This paper explores the integration of Ethereum blockchain, smart city concepts, and the InterPlanetary File System (IPFS), investigating the potential for implementing an Ethereum blockchain-based smart contract on a smart city system. Finally, the proposed architecture is simulated in a limited environment, yielding results that demonstrate its feasibility.

Port management is critical to the maritime transportation industry. Effective port management aims, among other things, to reduce the amount of time required to operate the cargo volume of the vessels. Numerous uncertainty factors, such as weather and mechanical issues, frequently affect maritime transportation, which can hamper port operations planning. The lack of certainty surrounding a number of relevant parameters makes efficient preparation for quayside operations difficult. As a result, when making decisions, it is critical to account for the possibility of uncertainty. The ability to deal with unfavorable and unpredictable events is one of the characteristics of a great practical solution. In this paper, we investigate a scenario in which machine learning techniques are used to predict data for both the berth allocation and the quay crane assignment problems. We model the problem as a mixed integer linear program with multiple objectives that takes berth allocation and quay crane assignment into account. We propose a genetic algorithm scheme to solve the problem. Crossover and mutation procedures are provided. Finally, managerial implications and future research directions are given.

Distributed Denial of Service (DDoS) attacks are becoming increasingly common and sophisticated, and supply chain networks are particularly vulnerable to these types of attacks due to their reliance on interconnected systems. Software-Defined Networking (SDN) has the potential to enhance resilience against DDoS attacks by providing a centralized control mechanism and the ability to reroute traffic dynamically. However, traditional methods for detecting and mitigating DDoS attacks in SDN-based networks may not be sufficient to protect against these threats fully. In this paper, we propose the use of machine learning techniques to detect and mitigate DDoS attacks in SDN-based supply chain networks. We will investigate how the centralized control mechanism of SDN can be leveraged to improve the effectiveness of machine learning-based DDoS attack detection and mitigation. Additionally, we evaluated these techniques' performance and effectiveness and discussed the trade-offs and limitations of using machine learning for DDoS attack detection and mitigation in SDN-based supply chain networks.

Blockchain technology provides a promising solution for collaborative economy systems by offering a decentralized, transparent, and secure platform. This is mainly accomplished through smart contracts, which are self-executing computer programs that facilitate, verify, and enforce the negotiation or performance of a contract. Digital tokens, on the other hand, are used to represent assets or currencies in these systems. Despite the benefits of Blockchain-based collaborative economy systems, significant security concerns are associated with them. These include the possibility of fraud, risk assessment, bugs in smart contracts, and cyber-attacks. For instance, attackers can exploit vulnerabilities in smart contracts to perform reentrancy and infinite loop attacks, leading to significant financial losses. To address these security challenges, this paper proposes integrating artificial intelligence models to prevent vulnerabilities in smart contracts and detect anomalies. Specifically, Graph Neural Networks models can be utilized to safeguard Blockchain-based collaborative economy platforms from attacks such as reentrancy and infinite loop attacks. According to the findings, this approach can accurately identify both normal and abnormal traffic and classify specific types of attacks. The framework's performance is further evaluated using various metrics to ensure its effectiveness in detecting anomalies, thereby providing an additional layer of security for Blockchain-based collaborative economy systems.

The Internet of Things (IoT) has grown exponentially over the past decade, but this growth has also raised a number of issues for the ongoing operation of IoT applications, including resource limitations, server overload, and the risk of improper use of private data. To address these challenges, Blockchain technology, which initially powered the crypto-currency Bitcoin, is gaining recognition as a solution that can enhance security and privacy. Blockchain (BC) provides several essential features, such as a consensus approach, peer-to-peer communications, trust without the need for a third party, and transactions controlled by conditions and functions through the use of smart contracts. Thus, BC technology is a suitable candidate for building a decentralized, autonomous Internet of Things system that addresses the issues raised by IoT. In this paper, we propose Secure Smart Home Communications based on the Ethereum BC and Smart Contract as a new design to solve the dilemma between the limited resources of IoT devices and the concerns of a centralized architecture. Quantitative and qualitative evaluations of the architecture under common threat models have highlighted its effectiveness in providing security and privacy for IoT applications.

The Software-Defined Networking (SDN) paradigm has introduced heightened flexibility and scalability to network infrastructure management. However, the centralized control plane inherent in SDN architectures is susceptible to an array of security vulnerabilities, necessitating the development of efficient and real-time anomaly detection systems. This paper presents a novel integrated methodology for real-time anomaly detection within SDN architectures, capitalizing on the synergies between Security Information and Event Management (SIEM) systems and advanced machine learning techniques to bolster network security. The proposed framework operates by seamlessly collecting and analyzing live network traffic data, promptly pinpointing potential anomalies, and subsequently correlating these events via the SIEM system. To enhance accuracy while mitigating false positives, machine learning algorithms are harnessed to accurately categorize network traffic into benign and malicious activities, dynamically adapting to evolving threat landscapes. Empirical validation is conducted through an exhaustive dataset of real-world network traffic, encompassing an extensive array of attack scenarios. Findings vividly underscore the efficacy of the amalgamated SIEM and machine learning-driven anomaly detection system, yielding impressive detection accuracy while maintaining notably low rates of false positives. Noteworthy is the system's intrinsic adaptability to emergent threats, culminating in an elevated caliber of network security and fortitude within the SDN domain. This contribution significantly enriches the realm of real-time anomaly detection research, endowing SDN architectures with a pioneering strategy to counteract intricate cyber threats effectively.

Edge computing offloads the data processing capacity to the user side, provides flexible and efficient computing services for the development of the smart city, and brings many security challenges. To enhance the security of data sharing in edge computing, a secured blockchain shared data in Software Defined Networking System (BCDS-SDN) framework is proposed to ensure secured transactions between edge nodes and the Cloud, control access, and verify trusted edge from malicious nodes. The integration of SDN and blockchain concepts gives us the power to control and verify the identity of edge nodes to protect the infrastructure from many types of attacks, such as MitM, compromised channels, adding malicious nodes, and DDoS attacks. The combination of edge computing and Blockchain in a BCDS-SDN solution provides a vast scale of storage systems, database servers, and authenticated computation to the end in a secure manner. Our findings contribute toward more SDN-based security of data-sharing by providing a testbed-based proof of the efficiency and performance of Blockchain technology in ensuring the security of data-sharing in the edge-computing environment.

This paper presents the findings of a field study conducted in Rabat, the capital of Morocco, utilizing the Wardriving technique to assess Wi-Fi network security. The study encompasses approximately 10,000 Wi-Fi networks situated in residential and administrative neighborhoods in Rabat. Through our comprehensive analysis, we observed that a substantial 89.42% of the networks use WPA2, suggesting that Wi-Fi security in Morocco compares favorably to that of developed countries. We also found that most networks don’t use default configurations, this indicates a proactive approach by network administrators to implement robust security measures. Moreover, our investigation revealed a balanced distribution of channels 1, 6, and 11, illustrating that network operators are mindful of potential interferences, particularly on channel 6, and have taken measures to mitigate such interferences effectively. Based on our results, we draw a positive conclusion that the Wi-Fi situation in the examined neighborhoods of Rabat is highly encouraging. The study highlights the efforts made by network administrators to secure their Wi-Fi infrastructures and optimize network performance, contributing to a safer and more reliable wireless environment for users. This research serves as a valuable reference for understanding the state of Wi-Fi security in Rabat and provides insights into the overall Wi-Fi landscape in the city. The data-driven conclusions can aid policymakers, businesses, and individuals in further enhancing Wi-Fi security practices to ensure the continued growth and stability of wireless connectivity in the region.

Software defined networks represent a new centralized network abstraction that aims to ease configuration and facilitate applications and services deployment to manage the upper layers. However, SDN faces several challenges that slow down its implementation such as security which represents one of the top concerns of SDN experts. Indeed, SDN inherits all security matters from traditional networks and suffers from some additional vulnerability due to its centralized and unique architecture. Using traditional security devices and solutions to mitigate SDN threats can be very complicated and can negatively effect the networks performance. In this paper we propose a study that measures the impact of using some well-known security solution to mitigate intrusions on SDN's performances. We will also present an algorithm named KPG-MT adapted to SDN architecture that aims to mitigate threats such as a Man in the Middle, Deny of Services and malware-based attacks. An implementation of our algorithm based on multiple attacks' scenarios and mitigation processes will be made to prove the efficiency of the proposed framework.

Software defined networks (SDNs) represent new centralized network architecture that facilitates the deployment of services, applications and policies from the upper layers, relatively the management and control planes to the lower layers the data plane and the end user layer. SDNs give several advantages in terms of agility and flexibility, especially for mobile operators and for internet service providers. However, the implementation of these types of networks faces several technical challenges and security issues. In this paper we will focus on SDN's security issues and we will propose the implementation of a centralized security layer named AM-SecP. The proposed layer is linked vertically to all SDN layers which ease packets inspections and detecting intrusions. The purpose of this architecture is to stop and to detect malware infections, we do this by denying services and tunneling attacks without encumbering the networks by expensive operations and high calculation cost. The implementation of the proposed framework will be also made to demonstrate his feasibility and robustness.