Bahaa Eddine Elbaghazaoui

The rapid digital transformation of education has accelerated the adoption of artificial intelligence (AI), cloud computing, and smart learning platforms, enabling personalized and adaptive learning experiences. However, this evolution has also increased exposure to cybersecurity threats, making educational institutions prime targets due to the sensitivity and volume of data they handle. This chapter examines key cybersecurity challenges in AI-driven educational environments, including threats such as phishing, ransomware, and data breaches, as well as vulnerabilities related to human behavior and system weaknesses. It proposes a comprehensive approach combining governance, technical safeguards, and user awareness. The chapter also highlights the role of machine learning in enhancing threat detection, predictive security, and automated responses, emphasizing the need for proactive and adaptive cybersecurity strategies.

The effectiveness of online tutoring systems largely depends on their ability to adapt to the individual needs of learners, to personalize learning activities, and to provide immediate and effective assessment and remediation. This effectiveness can only be ensured if accurate information is available regarding learners’ progress and learning profiles. In this article, we aim to propose a learner model tailored to the specificities of our academic support system, incorporating learning functions that enable personalized tutoring based on students’ needs. For this purpose, this study began with a literature review of existing learner models. We focused on five representative samples of the most widely used learner models in current learning systems: instructional management system-learner information package (IMS-LIP), public and private information for learners (PAPI), CARCHIOLO, knowledge on demand (KOD), and learner model for personalized adaptation (LMPA). We examined their characteristics and then compared them based on the following criteria: adaptability, user preferences, personalized learning, pedagogical requirements, assessment, and remediation, to evaluate their potential for integration into our system. The study revealed that these models present several limitations, which led us to propose a new learner model based on the PAPI and IMS-LIP standards. This proposal incorporates a semantic ontological structure that categorizes learner characteristics into six domains: preferences, pedagogy, administration, identification, learning, and assessment. The proposed model represents a promising solution for adapting learning processes to individual learner profiles, thereby fostering more effective and engaging educational experiences.

Weight initialization is a critical factor in training convolutional neural networks (CNNs), particularly in remote sensing (RS) applications where data is often high-dimensional, imbalanced, and noisy. This review explores traditional methods such as Random, Xavier, and He initialization, as well as modern strategies like MetaInit, GradInit, RGB-based, Laor, and convergence-aware approaches. These techniques are evaluated in the context of RS-specific challenges and benchmarked across architectures like VGG, ResNet, and DenseNet. Case studies in urban segmentation, SAR target recognition, and infrastructure quality assessment show that domain-sensitive initialization improves convergence speed, training stability, and classification accuracy. The review emphasizes the importance of selecting adaptive and data-aware initialization schemes that align with RS data characteristics. Overall, weight initialization should be treated not as a fixed preprocessing step but as a key design element for building robust, accurate, and scalable deep learning models in RS.

The proliferation of fake news threatens data integrity and public trust, challenging the foundations of modern data-driven systems. This chapter explores how Generative AI, particularly large language models (LLMs), can enhance fake news detection and support trustworthy data architectures. We review key techniques in misinformation detection and analyze the emerging role of GenAI in enabling automated content validation, explanation generation, and credibility assessment. The integration of these models into data pipelines introduces new opportunities but also raises concerns such as hallucinations, bias propagation, and ethical risks. We outline the main challenges and propose future research directions to design autonomous, explainable, and resilient systems capable of mitigating misinformation in real time while upholding transparency and data governance principles.

In Morocco, the escalating challenges in the education sector underscore the necessity for precise predictions and informed decision-making. Effective management of the education system depends on robust statistical data, which is crucial for guiding decisions, refining policies, and improving both the quality and accessibility of education. Reliable indicators are vital for ensuring efficiency, equity, and accuracy in educational planning and decision- making. Without dependable data, implementing effective policies, addressing the needs appropriately, and achieving positive outcomes becomes difficult. This paper aims to identify the optimal machine learning model for analyzing educational indicators by comparing a range of advanced models across a comprehensive set of metrics. The objective is to determine the most effective model for profiling relevant information and addressing predictive challenges with high accuracy.

In Morocco, the dropout rate in primary and secondary education remains high due to environmental, social, familial, and educational factors. To address this issue, students rely on private tutoring or online platforms. However, socio-economic disparities make private tutoring inaccessible to many, while technical and pedagogical challenges limit the effectiveness of online platforms, deepening educational inequalities. This article proposes a nationwide participatory tutoring approach involving educational administration and teachers to ensure equitable and quality learning. We analyze existing models to identify their limitations and propose a structured tutoring system tailored to different student profiles. This system is based on a specific algorithm that defines skill assessment, remediation, and progress tracking. Unified modeling language UML is used to structure and present our approach in detail. Then, we compare current Moroccan platforms, particularly Massar, with our system, evaluating student engagement, pedagogical monitoring, curriculum alignment, and remediation effectiveness. Finally, we discuss our results, highlighting our system’s potential to reduce learning gaps, improve education, and significantly decrease the dropout rate in Morocco.

The rapid rise of information sharing on social media has amplified the spread of fake news, making its detection increasingly critical. As fake news continues to proliferate, the need for efficient detection mechanisms has become more urgent to protect users from misinformation and disinformation. This paper presents a comparative analysis of multiple machine learning models for detecting text based fake news on social media platforms. Using models such as gradient boosting, XGBoost, and linear support vector classifier (SVC) on the Infor mation Security and Object Technology (ISOT) fake news dataset, the study demonstrates that gradient boosting achieves the highest accuracy of 99.61%, while XGBoost provides a strong balance with 99.59% accuracy and a signifi cantly lower execution time, making it more suitable for real-time applications. These results offer valuable insights into the trade-offs between accuracy and computational efficiency, contributing to the development of more practical de tection systems and future research in the field.

In the fast-paced world of software development, integrating security into the DevOps pipeline is essential for achieving Continuous Protection. This chapter provides a comprehensive overview of DevSecOps, an approach that unifies security with development and operations to create secure, reliable, and scalable software systems. The chapter begins by examining the challenges of traditional security in DevOps and introduces key principles of DevSecOps, such as early vulnerability detection, security automation, and fostering a security-first culture. Practical insights into implementing security tools, managing risks, and enhancing collaboration among cross-functional teams are provided. Readers will gain an understanding of how DevSecOps can be leveraged to ensure software remains secure without compromising on agility and innovation.

DataOps is crucial for managing complex data pipelines and driving efficient data analytics, but it introduces significant security challenges as data flows through ingestion, transformation, storage, and distribution stages. Each phase exposes unique vulnerabilities that threaten data integrity, confidentiality, and compliance. This chapter outlines a structured framework for embedding security into DataOps workflows, focusing on methods like encryption, access control, and real-time monitoring to safeguard data without disrupting operations. Leveraging advanced tools, including Security Orchestration, Automation, and Response (SOAR) platforms and cloud-native security solutions, we demonstrate how to automate threat detection and response for scalable data environments. Case studies from industries such as healthcare and finance illustrate successful implementation, offering practical insights and lessons learned. This framework equips data and security professionals to build secure, resilient pipelines, fostering trust and agility in data ecosystems.