LELatifa Er-Rajy

Latifa Er-Rajy

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Latifa Er-Rajy has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • An Efficient Face Recognition Model Based on ViT Architecture

    by Er-Rajy Latifa, El Kiram My Ahmed, Lahihab Oussama, El Ghazouani Mohamed

  • Enhancing Security in Smart Cities: A Comprehensive Review of Threats and Countermeasures

    by Mariya Ouaissa, Mariyam Ouaissa, Soukayna Riffi Boualam, Sarah El Himer, Zakaria Boulouard, Latifa Er-Rajy

  • Open Access

    Optimal Method Combining Blockchain and Multi-Agent System to Ensure Data Integrity and Deduplication in the Cloud Environment

    by Mohamed El Ghazouani, Abdelouafi Ikidid, Charafeddine Ait Zaouiat, Layla Aziz, Moulay Youssef Ichahane, Latifa Er-Rajy

    Cloud computing (CC) refers to the transmission, storage, and processing of any type of information at a location that is not owned or controlled by the information owner. This information can be stored and accessed anytime, from anywhere, and using any device. However, several challenges threaten the deployment of cloud computing technology within organizations, including user privacy, data integrity, and managing the retention of the vast amount of data that will be stored and analyzed in this environment. In recent years, various data integrity checking systems and data storage mechanisms have been proposed to address these diverse challenges. Nevertheless, some protocols do not guarantee data confidentiality against auditors during the auditing process, while others do not provide batch auditing. Additionally, the majority of these protocols do not support the deduplication technique. Therefore, in this research work, the security features of blockchain technology and those of multi-agent systems (MAS) have prompted us to propose models that enable both data deduplication, saving storage space, and data integrity auditing, efficiently verifying the accuracy of data outsourced to CC environments. Implementation findings indicate that the suggested system is highly feasible and applicable in real-world scenarios.


  • Open Access

    GetFace: A Real-time Face Detection Solution for Surveillance Footage

    by Er-Rajy Latifa, El Kiram My Ahmed, El Ghazouani Mohamed

    Recently, facial recognition technology has advanced significantly and become widely used. However, detecting faces from surveillance camera footage in real time can be a difficult task due to a variety of factors. One major challenge is that the quality of the footage may be poor, with low resolution or high levels of noise. Additionally, lighting conditions can also make it difficult to detect faces, especially in low light environments. Furthermore, faces may be partially obscured by objects such as hats or sunglasses, or by changes in pose or expression. Finally, the number of faces in a given scene can also make it difficult to detect and track individuals in real-time. time is the presence of occlusions. Occlusions occur when an object or person blocks the view of a face, making it difficult or impossible to detect. Additionally, faces may be captured at different angles and scales, which can further complicate the detection process. Another factor that makes face detection difficult is that faces can appear differently due to various factors such as age, gender, race, and facial expressions. This can make it hard for the algorithm to generalize and detect all types of faces. In this article, we propose GetFace, an intelligent system for enhancing surveillance footage. GetFace uses CNNs, super-resolution methods, human shape and face detection techniques, Wiener filter, and face clustering to improve the image quality.

  • Open Access

    Real-time Human Body Detection in Surveillance Footage Using Computer Vision Algorithms

    by Latifa Er-Rajy, My Ahmed El Kiram, Mohamed El Ghazouani

    The detection of human bodies in real-time surveillance footage is a crucial problem in the field of computer vision with various applications in security, safety, and monitoring. In this paper, we present our computer vision system designed for real-time human body detection in surveillance footage. The system is optimized for both efficiency and accuracy, making it suitable for use in real-world scenarios. We have divided the system into several stages including data collection, feature extraction, model selection, model training, real-time deployment, and post-processing. To evaluate our system, we conducted thorough evaluations on a large dataset of surveillance footage and found it to achieve high accuracy and efficiency. The results of our extensive evaluation demonstrate the tool's effectiveness and potential for widespread use in various applications. The proposed system is a valuable tool for practical applications, providing a reliable and cost-effective solution for real-time human body detection and can be easily integrated into existing surveillance systems. Our contribution to the advancement of computer vision and its applications in real-world scenarios, particularly in the field of security and surveillance, is significant. The paper concludes with a discussion of future work aimed at further improving the tool's capabilities and applications.

  • Android Applications Analysis Using PerUpSecure

    by Latifa Er-Rajy, My Ahemed El Kiram, Mohamed El Ghazouani

  • Android: Deep look into Dalvik VM

    by Er-Rajy Latifa, El Kiram My Ahmed

    Today, Smartphones are very powerful, and many of its applications use wireless multimedia communications. Prevention from the external dangers (threats) has grown up to be a big concern for the experts these days. Android security has become a very important issue because of the unrestricted application it provides and the feature that make it very easy for anyone to develop and published it on Play store. Some work has previously been done on the Android security model, including numerous analyses of the model and frameworks aimed at enforcing security standards. In this article, we explain the architecture of Android operating system, we study and we look for a process model of Android's virtual machine Dalvik. We also study the liaison between the Dalvik virtual machine processes and the connection between the Dalvik processes and the processes of Android through analysis and research the role and the boot process of Zygote in Dalvik virtual machine startup process. This paper discusses an example of attacks based on Dalvik VM. By the end, we propose a simple system that can effectively detect Android's applications issues and solve them.


  • How far android is secure?

    by Latifa Er-Rajy, My Ahmed El Kiram

    In the last few years, Android becomes one of the most popular mobile operating system in the whole world, as a side effect of this popularity, Android becomes the most preferred destination of hackers with different aims, some of them look for making money and others are just having fun by storming the privacy of the others without their permission. Nowadays, Android security has become a big problem because of the free application provided and functionality that make it very easy for anyone to develop it. However, various systems have been proposed by a large number of researchers to address this problem, including the system developed by Google called "Bouncer". In this article, we focus on several security issues related to the Android smart phone. In addition, we have a simple scheme of defense that can effectively detect and address some of these issues in the form of android application we called PermisSecure.