Journal Articles
Permanent URI for this collectionhttps://dspace.univ-soukahras.dz/handle/123456789/25
Browse
11 results
Search Results
Item Vulnerability of the Dynamic Array PIN Protocol(Ingénierie des Systèmes d’Information, 2022-02-28) Samir Chabbi; Djalel ChefrourWe recently proposed the Dynamic Array PIN protocol (DAP), which is a novel approach for user authentication on Automated Teller Machines. DAP replaces bank cards with smartphones that support Near Field Communication (NFC) and allows a user to enter his PIN code in a secure way. We showed that DAP is resistant to 13 different attacks and is therefore better and more cost effective than several other solutions from the literature. However, after carrying a deeper analysis we found that DAP is vulnerable to a complex attack that might lead to unauthorized transactions on ATMs if the user smartphone and his PIN code are both stolen. In this paper we expose how the user PIN code can be discretely discovered using multiple eavesdropping videos or camera records. We also propose several fixes for this vulnerability.Item An Intersection Attack on the CirclePIN Smartwatch Authentication Mechanism(IEEE Internet of Things Journal, 2024-04-01) Djalel Chefrour; Yasser Sedira; Samir ChabbiWe present a thorough security analysis of a recent smartwatch authentication mechanism called CirclePIN, which was considered resilient to several attacks, including shoulder surfing and video recording. This mechanism avoids the direct entry of the personal identification number (PIN) by using consecutive screens of random colors that fool the attacker. We disclose a vulnerability in CirclePIN inherent to the way in which the users match the random colors to their PINs’ digits and we illustrate how to exploit it with an intersection attack. This attack uses the information extracted from multiple video recordings of legitimate authentication sessions. We prove that it has a high probability of revealing the user PIN with only three video recordings and always succeeds with five. Our proof is twofold. We formulate the theoretical probability of success for the attack as a function of the number of available video recordings. Then, we validate this formula with a simulation of a large number of attacks to compute their experimental probability of success. In our estimation, manual information extraction takes around 1 min per exploitable video recording. So, a complete intersection attack is cost effective in terms of time, as it lasts 5 min or less.Item K-CAE: Image Classification Using Convolutional AutoEncoder Pre Training and K-means Clustering(Slovene Society Informatika, 2023) Aida Chefrour; Samia DrissiThe work presented in this paper is in the general framework of classification using deep learning and, more precisely, that of convolutional Autoencoder. In particular, this last proposes an alternative for the processing of high-dimensional data, to facilitate their classification. In this paper, we propose the incorporation of convolutional autoencoders as a general unsupervised learning data dimension reduction method for creating robust and compressed feature representations for better storage and transmission to the classification process to improve K-means performance on image classification tasks. The experimental results on three image databases, MNIST, Fashion-MNIST, and CIFAR-10, show that the proposed method significantly outperforms deep clustering models in terms of clustering quality.Item Unsupervised Deep Learning: Taxonomy and Algorithms(Slovene Society Informatika, 2022) Aida Chefrour; Labiba Souici-MeslatiClustering is a fundamental challenge in many data-driven application fields and machine learning techniques. The data distribution determines the quality of the outcomes, which has a significant impact on clustering performance. As a result, deep neural networks can be used to learn more accurate data representations for clustering. Many recent studies have focused on employing deep neural networks to develop a clustering-friendly representation, which has resulted in a significant improvement in clustering performance. We present a systematic survey of clustering with deep learning in this study. Then, a taxonomy of deep clustering is proposed, as well as some sample algorithms for our overview. Finally, we discuss some exciting future possibilities for clustering using deep learning and offer some remarksItem Dynamic array PIN: A novel approach to secure NFC electronic payment between ATM and smartphone(Taylor & Francis, 2020-06-04) Samir Chabbi; Rachid Boudour; Fouzi Semchedine; Djalel ChefrourNear Field Communication (NFC) technology has been used recently for electronic payment between an Automated Teller Machine (ATM) and a Smartphone. It is threatened by several attacks that can steal the user personal data like the password or the Personal Identification Number (PIN). In this paper, we present Dynamic Array PIN (DAP), a novel approach for user authentication on a Smartphone that uses NFC electronic payment with an ATM. Our analysis and experimentation prove that this technique protects against thirteen different attacks and is cost-effective in terms of required hardware, authentication time, computing power and storage space.Item Science Education in Algeria(2022-01-19) Hafed ZARZOURThroughout history, science education has played a vital role in developing and modernizing the countries. The education in Algeria has been developing for the last years as a result of several reforms undertaken for enhancing the quality of learning and teaching in the whole education system, ranging from the primary school to higher education. Hence, this book chapter attempts to present the science education in Algeria. It starts by providing some information about the geographical location, population, and political system, as well as outlining the economic, technologies, and cultural development in the country. It then presents an overview of the education development and the current situation of science education in Algeria. The present chapter further explores the requirements for future development of science education. Finally, challenges and strategies, reflections and issues, and future pathways are discussed in the hope of improving the leaning and teaching for omorrow’s world.Item Using Deep Learning for Positive Reviews Prediction in Explainable Recommendation Systems(2022-10-26) Hafed ZARZOUR, Mohammad Alsmirat and Yaser JararwehItem Using K-means Clustering Ensemble to Improve the Performance in Recommender Systems(2022-10-26) Hafed ZARZOUR; Faiz Maazouzi; Mohammad Al-Zinati; Amjad Nusayr; Mohammad Alsmirat; Mahmoud Al-Ayyoub; Yaser JararwehItem Unsupervised Deep Learning: Taxonomy and Algorithms(2022-12-14) Aida CHEFROUR and SOUICI-MESLATI LabibaItem Evolution of network time synchronization towards nanoseconds accuracy: A survey(Elsevier, 2022-07) Djalel ChefrourWe expose the state of the art in the topic of network time synchronization. Many distributed applications require a common notion of time to function properly. Without time synchronization, the nodes clocks will drift and report different values for the same instant. This problem is exacerbated by varying network delays between the cooperating nodes. Our survey covers how this issue is tackled by standard time synchronization mechanisms and a representative range of recent research works. We expose how some of them achieve micro and nanoseconds accuracy in wired networks. The reviewed techniques are classified in two categories based on whether they change the hosts clocks or not. The latter category includes schemes that detect and remove clock skew from network traffic trace. We discuss the advantages and drawbacks of the techniques in each category; compare them according to their application environment, accuracy and cost; and conclude this survey with a summary of learned lessons and insights into future work.