2025Other
Intrusion Recognition Coupled with a Heuristic Attributes Selection Method Using Neural Networks
Berlin Hervé Djionang Lekagning, Gilbert Tindo, Roger Atsa Etoundi
Communications in computer and information science
Checking session…
INF
Chargé de Cours
Scientific activity
Researcher profile
Faculty researcher at the University of Yaoundé I. Grade: Chargé de Cours.
Scientific publications
Berlin Hervé Djionang Lekagning, Gilbert Tindo, Roger Atsa Etoundi
Communications in computer and information science
Léonie Tamo Mamtio, Gilbert Tindo
Revue Africaine de la Recherche en Informatique et Mathématiques Appliquées
Electronic voting systems have become a powerful technology for the improvement of democracy by reducing the cost of elections, increasing voter turnout and even allowing voters to directly check the entire electoral process. End-to-end (E2E) verifiability has been widely identified as a critical property for the adoption of such voting systems for electoral procedures. Moreover, one of the pillars of any vote, apart from the secret of the vote and the integrity of the result, lies in the transparency of the process, the possibility for the voters "to understand the underlying system" without resorting to the competences techniques. The end-to-end verifiable electronic voting systems proposed in the literature do not always guarantee it because they require additional configuration hypotheses, for example the existence of a trusted third party as a random source or the existence of a random beacon. Hence, building a reliable verifiable end-to-end voting system offering confidentiality and integrity remains an open research problem. In this work, we are presenting a new verifiable end-to-end electronic voting system requiring only the existence of a coherent voting board, fault-tolerant, which stores all election-related information and allows any party as well as voters to read and verify the entire election process. The property of our system is information guaranteed given the existence of the bulletin board, the involvement of the voters and the political parties in the process. This involvement does not compromise the confidentiality nor integrity of the elections and does not require cryptographic operations on the voters account. Les systèmes de vote électronique sont devenus une technologie puissante pour amé-liorer la démocratie en réduisant le coût des élections, en augmentant la participation des électeurs et en permettant même aux électeurs de vérifier directement l'ensemble de la procédure électorale. Cependant, la vérification de bout en bout (E2E) a été largement identifiée comme une propriété critique pour l'adoption de tels systèmes de vote en réel pour des procédures électorales. Par ailleurs, l'un des piliers de tout scrutin, outre le secret du vote et l'intégrité du résultat, réside dans la trans-parence du processus, la possibilité pour les électeurs "de comprendre le système sous-jacent" sans avoir recours aux compétences techniques. Les systèmes de vote électronique vérifiables de bout en bout proposés dans la littérature ne le garantissent pas toujours car ils nécessitent des hypothèses de configuration supplémentaires par exemple l'existence d'un tiers de confiance comme source de hasard, l'existence d'une balise aléatoire. Ainsi, construire un système de vote vérifiable de bout en bout fiable offrant la confidentialité et l'intégrité reste un problème de recherche ouvert. Dans ce tra-vail, nous présentons un nouveau système de vote électronique vérifiable de bout en bout nécessitant uniquement l'existence d'un babillard de vote cohérent, tolérant aux pannes, qui stocke toutes les in-formations relatives aux élections et permet à tout parti ainsi qu'aux électeurs de lire et vérifier le processus d'élection complet. La propriété de vérification de bout en bout de notre système est une information garantie compte tenu de l'existence du babillard, de l'implication des électeurs et des par-tis politique dans le processus. Cette implication ne compromet ni la confidentialité ni l'intégrité des élections et ne nécessite pas d'opérations cryptographiques pour le compte de l'électeur.
Berlin H. Lekagning Djionang, Gilbert Tindo
Global Journal of Computer Science and Technology
Heather A. Berlin, Gilbert Tindo
International Journal of Computer Applications
Neural networks are artificial learning systems. For more than two decades, they have help for detecting hostile behaviors in a computer system. This review describes those systems and theirs limits. It defines and gives neural networks characteristics. It also itemizes neural networks which are used in intrusion detection systems. The state of the art on IDS made from neural networks is reviewed. In this paper, we also make a taxonomy and a comparison of neural networks intrusion detection systems. We end this review with a set of remarks and future works that can be done in order to improve the systems that have been presented. This work is the result of a meticulous scan of the literature.
Norbert Tsopzé, Engelbert Mephu Nguifo, Gilbert Tindo
HAL (Le Centre pour la Communication Scientifique Directe)
International audience
Norbert Tsopzé, Engelbert Mephu Nguifo, Gilbert Tindo
Techniques et sciences informatiques
This paper presents a new method of artificial neural network architecture definition. This approach shows how the concept lattice could help to define the artificial neural network architecture. We will also present the existing approaches that are reported in the litterature. Finally a comparative study is described and discussed.
Norbert Tsopzé, Engelbert Mephu Nguifo, Gilbert Tindo
Artificial Neural Networks classifiers have many advantages such as: noise tolerance, possibility of parallelization, better training with a small quantity of data.... Coupling neural networks with an explanation component will increase its usage
Norbert Tsopzé, Engelbert Mephu Nguifo, Gilbert Tindo
The current development of knowledge discovery domain has pointed out a high number of applications where the need of explanation is at the heart of the process. Using neural networks for those applications requires to be able to provide a set of rules extracted from the trained neural networks, that can help the user to comprehend the learning process. The current literature reports two kinds of rules: `if condition then conclusion' (called if-then) and `if m of conditions then conclusion' (also called MofN). We propose a new method able to extract one intermediate structure (called generators list) from which it is possible to extract both forms of rules. The extracted structure is a generic representation that gives the possibility to the user to visualize each form of rules extracted from the multilayer artificial neural networks.
Engelbert Mephu Nguifo, Norbert Tsopzé, Gilbert Tindo
Studies in computational intelligence
Engelbert Mephu Nguifo, Norbert Tsopzé, Gilbert Tindo
Lecture notes in computer science
Norbert Tsopzé, Engelbert Mephu Nguifo, Gilbert Tindo
Abstract. Multi-layer neural networks have been successfully applied in a wide range of supervised and unsupervised learning applications. As they often produce incomprehensible models they are not widely used in data mining applications. To avoid such limitations, comprehensive models have been previously introduced making use of an apriori knowledge to build the network architecture. They permit to neural network methods to deserve a place in the tool boxes of data mining specialists. However, as the apriori knowledge is not always available for every new dataset, we hereby propose a novel approach that generates a concept semi-lattice from initial dataset, to directly build the neural network architecture. Carried out experiments showed the soundness and efficiency of our approach on various UCI. 1
Norbert Tsopzé, Engelbert Mephu Nguifo, Gilbert Tindo
EGC eBooks
Michel Cosnard, Maurice Tchuenté, Gilbert Tindo
Complex Systems
We st udy th e sequences generated by neuronal recurrence equat ions of th e form X n = l [~l then there is a neuronal recurrence equat ion with memory length kr that generates a sequence of period lcmlp «, . . . , Pr )1', where lem deno tes the least common multiple. As an applicat ion we show tha t , for any integer ko, there is a neuronal equa tion with memory lengt h 3k , k 2:: ko, that generates a sequence of period O(k3 ) .
Une methode de conception du modele de simulation d'un systeme discret a l'aide des automates cellulaires est etudiee et appliquee a la construction de deux modeles de simulation de certains phenomenes naturels: la competition entre especes et l'evolution des especes. Ensuite une famille d'automates cellulaires finis a une dimension est etudiee. En particulier l'existence d'un plus long cycle limite dans le graphe de transition de ces automates est examinee. Une methode pour determiner tous les automates cellulaires de la famille presentant dans leur comportement dynamique un tel cycle limite est exhibee. Enfin, la generation de suites pseudo-aleatoires par une famille d'automates cellulaires reversibles a une dimension est analysee. On obtient un generateur programmable, realisable en circuits integres sous forme de carte specialisee qu'on pourrait adjoindre a un ordinateur hote. Des reseaux systoliques sont proposes pour une telle realisation pratique
Norbert Tsopzé, Engelbert Mephu Nguifo, Gilbert Tindo
HAL (Le Centre pour la Communication Scientifique Directe)
National audience
Researcher profile
Scientific publications
1 publication
1 publication
2 publications
1 publication
2 publications
2 publications
1 publication
1 publication
3 publications
1 publication
1 publication
Collaborations