With the fast up-growth and evolution of new information communication technologies due to factor spread universal-connected objects, an ample amount data has accumulated become available for every individual or organization in form a set big datasets. Today world needs exploit those cumulated datasets understand interpret existent phenomena other joint problems different sectors (e.g., economic, health, education, security) enhance well-being by introducing intelligent automatic processes...

Internet of things (IoT) dramatically influences our daily lives in several domains, ranging from teeny wearable devices to large industrial systems. IoT technology aims enhance humans life quality. Nevertheless, is vulnerable various cyberattacks and needs challenging techniques order achieve their security. The principal objective security protect the privacy customers, data integrity confidentiality, infrastructures devices, likewise, ensure availability services provided by an ecosystem....

Drowsy driving poses a significant challenge to road safety worldwide, contributing thousands of accidents and fatalities annually. Despite advancements in driver drowsiness detection (DDD) systems, many existing methods face limitations such as intrusiveness delayed reaction times. This research addresses these gaps by leveraging facial analysis state-of-the-art machine learning techniques develop real-time, non-intrusive DDD system. A distinctive aspect this is its systematic assessment...

Large Language Models (LLMs), like GPT and BERT, have significantly advanced Natural Processing (NLP), enabling high performance on complex tasks. However, their size computational needs make LLMs unsuitable for deployment resource-constrained devices, where efficiency, speed, low power consumption are critical. Tiny (TLMs), also known as BabyLMs, offer compact alternatives by using compression optimization techniques to function effectively devices such smartphones, Internet of Things (IoT)...

<title>Abstract</title> Mask detection has emerged as an essential technology for ensuring safety and compliance in both public private settings. This paper presents end-to-end application utilizing Vision Wake Words (VWW) within the realm of Tiny Machine Learning (TinyML) to detect mask adherence real-time. Capitalizing on efficient MobileNetV2 architecture with Depthwise Separable Convolutions, our model minimizes memory foot- print computational demands Microcontroller Units (MCUs). We...

Cloud computing is becoming increasingly a magical solution and widely adopted technology for delivering services over the Internet thanks to its diverse benefits, including on demand, reducing costs, sharing configuring resources, high scalability flexibility. However, with emergence of this technology, concept security privacy has become major barrier cloud adoption. Indeed, many research works have been done identify issues. It in context that paper, we will provide new model (CSPM) into...

Confidentiality is among the most important obstacles for widespread adoption of cloud services. In fact, researchers have invented a new promising form encryption, homomorphic that can be considered as an effective way to overcome these obstacles. Since computing environment more threatened by attacks and since consumers often use resource-constrained devices access services, encryption schemes must promoted, in terms security level running time, work efficiently. At EMENA-TSSL’16, we...

Blockchain (BC) technology has recently gained significant popularity due to its ability provide a secure and decentralized platform for data storage transactions. There are tens of thousands BC-based cryptocurrencies apps. However, the proof work consensus mechanism used by most BC networks requires energy consumption, leading concerns about environmental impact. According Cambridge Bitcoin Electricity Consumption Index, estimated annual electricity consumption mining in 2022 was...

The application of tiny machine learning (TinyML) in human-computer interaction is revolutionizing gesture recognition technologies. However, there remains a significant gap the literature regarding effective complex scripts, such as Arabic, real-time applications. This research aims to bridge this by leveraging TinyML for accurate Arabic numbers and simple letters through gesture-based air handwriting. For first time, we introduce novel deep (TinyDL) model that utilizes lightweight...

In an era where the demand for efficient and practical machine learning (ML) solutions on resource-constrained devices is evergrowing, realm of tiny (TinyML) emerges as a promising frontier. Motivated by need lightweight, low-power models that can be deployed edge devices, this research paper presents innovative TinyML model tailored to recognize Arabic hand gestures executed in mid-air. With primary emphasis precise classification numbers through these expressive movements, unveils...

With the emergence of cloud computing, concept information security has become a major issue. Indeed, such system is greatest concern computer scientists, providers and organizations who want to adopt benefit from these services. Cloud computing must implement concepts ensuring network security, hardware, data storage strategies control access All elements help preserve availability services associated with Cloud, better satisfy clients acquire build their trust. However, even if in servers...

Thanks to several advantages offered by cloud computing, such as: reducing costs, high services scalability and flexibility. Cloud computing has become a widely adopted technology for delivering over the Internet. However, fear of seeing sensitive data be processed in clear major barrier adoption. Indeed, researchers have stressed useful technique called "homomorphic encryption", this allows specific type computations performed on encrypted without decrypting it The encryption schemes that...

Software-defined networking (SDN) has emerged as a promising approach for managing network infrastructure through centralized controller. However, the dynamic nature of SDN makes it susceptible to security threats, including DoS and DDoS attacks. Intrusion detection systems (IDS) based on machine learning (ML) can efficiently detect mitigate these This study compares two ML models, namely support vector machines (SVM) artificial neural networks (ANN), intelligent intrusion in SDN. To assess...

Nowadays, many Moroccan universities are working on digitizing their certifications. Digital certificates (e.g., official academic transcript, registration certificate, diploma) secure by digital signatures provided Barid eSign. To have a the student needs to send request. After successful verification and validation administrator, document desired will be signed university’s heads sent student’s account. All documents stored central server for authenticity verification. Herein, we overview...

Block chain (BC) is a relatively new technology; which has attracted much attention recently. It been developed rapidly and can be used in many applications of various domains such as decentralized approaches. Indeed, companies, even worldwide governments, are now using BC technology to improve the security, scalability, efficiency their services. In this paper, we provide an overview security. We start with basics technology. Next, give primary security attacks. Finally, present countermeasures.

Since the emergence of cloud paradigm, fear losing privacy sensitive data has become a main barrier to services adoption. Indeed, researchers have stressed useful technique that can address this barrier. This called "homomorphic encryption", is an encryption form supports operations on encrypted data. Unfortunately, many attacks make homomorphic schemes insecure. These efficiently achieve results when adopting these protect confidentiality in environment, owing long time storage by same key....