Ouarda Lounis

Dr. Ouarda Lounis

Intelligent Systems Engineering, National Higher School of Artificial Intelligence, Algiers, Alger, Algeria
orcid
AI & Cybersecurity Researcher | Open to Collaboration

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2014
Verified
Conference Paper
Closed access
SBSalah Eddine Benaicha
Salah Eddine Benaicha
LSLalia Saoudi
Lalia Saoudi
SGSalah Eddine Bouhouita Guermeche
Salah Eddine Bouhouita Guermeche
Ouarda LounisOuarda Lounis
Ouarda Lounis
In this paper, we present a Genetic Algorithm (GA) approach with an improved initial population and selection operator, to efficiently detect various types of network intrusions. GA is used to optimize the search of attack scenarios in audit files, thanks to its good balance exploration / exploitation; it provides the subset of potential attacks which are present in the audit file in a reasonable processing time. In the testing phase the Network Security Laboratory-Knowledge Discovery and Data Mining (NSL-KDD99) benchmark dataset has been used to detect the misuse activities. By combining the IDS with Genetic algorithm increases the performance of the detection rate of the Network Intrusion Detection Model and reduces the false positive rate.

1 January 2023 in Journal of Intelligent Systems
Verified
Journal Article
Open access
PDF file
Ouarda LounisOuarda Lounis
Ouarda Lounis
MBMalika Bourenane
Malika Bourenane
BBBouderah Brahim
Bouderah Brahim
An intrusion detection system plays an essential role in system security by discovering and preventing malicious activities. Over the past few years, several research projects on host-based intrusion detection systems (HIDSs) have been carried out utilizing the Australian Defense Force Academy Linux Dataset (ADFA-LD). These HIDS have also been subjected to various algorithm analyses to enhance their detection capability for high accuracy and low false alarms. However, less attention is paid to the actual implementation of real-time HIDS. Our principal objective in this study is to create a performant real-time HIDS. We propose a new model, “Better Similarity Algorithm for Host-based Intrusion Detection System” (BSA-HIDS), using the same dataset ADFA-LD. The proposed model uses three classifications to represent the attack folder according to certain criteria, the entire system call sequence is used. Furthermore, this work uses textual distance and compares five algorithms like Levenshtein, Jaro–Winkler, Jaccard, Hamming, and Dice coefficient, to classify the system call trace as attack or non-attack based on the notions of interclass decoupling and intra-class coupling. The model can detect zero-day attacks because of the threshold definition. The experimental results show a good detection performance in real-time for Levenshtein/Jaro–Winkler algorithms, 99–94% in detection rate, 2–5% in false alarm rate, and 3,300–720 s in running time, respectively.

1 August 2014
Verified
Conference Paper
Open access
Ouarda LounisOuarda Lounis
Ouarda Lounis
SGSalah Eddine Bouhouita Guermeche
Salah Eddine Bouhouita Guermeche
LSLalia Saoudi
Lalia Saoudi
Nowadays, the security of applications and Web servers is a new trend that finds its need on the Web. The number of vulnerabilities identified in this type of applications is constantly increasing especially SQL injection attack. It is therefore necessary to regularly audit Web applications to verify the presence of exploitable vulnerabilities. Web vulnerability scanner WASAPY is one of the audit tool, it uses an algorithm which bases on a classification techniques of pages obtained by sending HTTP requests especially formatted. We propose in this paper a new algorithm which was built in a vision to improve rather to supplement the logic followed in modeling WASAPY tool. The tool was supplemented by a new class reflecting the legitimate appearance or referential, therefore, the detection mechanism was solidly built on a statistic in a fairly clear mathematical framework described by a simple geometric representation or interpretation.

1 July 2015
Verified
Conference Paper
Closed access
Ouarda LounisOuarda Lounis
Ouarda Lounis
BMBourenane Malika
Bourenane Malika
In recent years, information systems have seen an amazing increase in attacks. Intrusion detection systems have become the mainstream of information assurance. While firewalls and the two basic systems of cryptography (symmetric and asymmetric) do provide some protection, they do not provide complete protection and still need to be supplemented by an intrusion detection system. Most of the work done on the IDS is based on two approaches; the anomaly approach and misuse approach. Each of these approaches whether they are implemented in HIDS or NIDS have weaknesses. To respond these limitations, we propose a new way of seeing in intrusion detection systems. This vision can be described as follows: "Instead of taking and analyzing each attack separately one from the other (have several signature for each type of attack knowing that there is various attacks and several variant of these attacks) or, instead of analyzing log files of the system, so why not see the consequences of these attacks and try to ensure that the security properties affected by these attacks will not be compromise". To do so, we will take the language which is realized by Jonathan Rouzauld Cornabas to modelize the system's entities to protect. This paper represents only the idea on which we will base on, in order to design an effective IDS in the operating system running in user space.

1 January 2022 in Journal of Intelligent Systems
Verified
Journal Article
Open access
PDF file
Ouarda LounisOuarda Lounis
Ouarda Lounis
MBMalika Bourenane
Malika Bourenane
NYNacer Eddine Yousfi
Nacer Eddine Yousfi
BBBouderah Brahim
Bouderah Brahim
Policy Interaction Graph Analysis is a Host-based Intrusion Detection tool that uses Linux MAC Mandatory access control policy to build the licit information flow graph and uses a detection policy defined by the administrator to extract illicit behaviour from the graph. The main limitation of this tool is the generation of a huge signature base of illicit behaviours; hence, this leads to the use of huge memory space to store it. Our primary goal in this article is to reduce this memory space while keeping the tool’s efficiency in terms of intrusion detection rate and false generated alarms. First, the interactions between the two nodes of the graph were grouped into a single interaction. The notion of equivalence class was used to classify the paths in the graph and was compressed by using a genetic algorithm. Such an approach showed its efficiency compared to the approach proposed by Pierre Clairet, by which the detection rate obtained was 99.9%, and no false-positive with a compression rate of illicit behaviour signature database reached 99.44%. Having these results is one of the critical aspects of realizing successful host-based intrusion detection systems.

1 January 2014 in International Journal of Advanced Computer Science and Applications
Verified
Journal Article
Open access
PDF file
Ouarda LounisOuarda Lounis
Ouarda Lounis
BGBouhouita Guermeche
Bouhouita Guermeche
LSLalia Saoudi
Lalia Saoudi
SBSalah Benaicha
Salah Benaicha
Nowadays, the security of applications and Web servers is a new trend that finds its need on the Web. The number of vulnerabilities identified in this type of applications is constantly increasing especially SQL injection attack. It is therefore necessary to regularly audit Web applications to verify the presence of exploitable vulnerabilities. Web vulnerability scanner WASAPY is one of the audit tool, it uses an algorithm which bases on a classification techniques of pages obtained by sending HTTP requests especially formatted. We propose in this paper a new algorithm which was built in a vision to improve rather to supplement the logic followed in modeling WASAPY tool. The tool was supplemented by a new class reflecting the legitimate appearance or referential, therefore, the detection mechanism was solidly built on a statistic in a fairly clear mathematical framework described by a simple geometric representation or interpretation.