Informatique

Permanent URI for this collection

http://dspace.univ-skikda.dz:4000/handle/123456789/187

Browse

Browsing Informatique by Author "Mazouzi , Smaine"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A New Information-Based Heuristic for Distributed DDoS Detection and Mitigation: Distributed and Collaborative DDoS Detection
    (International Journal of Organizational and Collective Intelligence Volume 12 • Issue 4, 2022) Nafir , Abdenacer; Mazouzi , Smaine; Chikhi ,Salim
    In this paper a novel collective method for DDoS detection is introduced. The method is distributed and implemented as a multi-agent system, and where local decision is based on an informationbased heuristic, namely the entropy. According the calculated entropy a router exchange data with its neighbors aiming at collectively decide if a DDoS is ongoing or not. Most of the works of the literature that are based on the entropy they have used source addresses. The authors’ method is based on the entropy of the distances traveled by the packets, so spoofing IP packets will be hard to perform by hackers. Each router combines its decision with those of its neighbors. Such a collective detection allows to apply defense against the attack despite the victim is out of service or cannot perform DDoS mitigation because the traffic is congested in its neighborhood. Conducted experiments using the platform OMNet++ show the potential of the new method for efficient collaborative and distributed detection and mitigation of DDoS attacks.
  • Thumbnail Image
    Item
    Self-Adaptation Through Reinforcement Learning Using a Feature Model
    (International Journal of Organizational and Collective Intelligence Volume 12 • Issue 4, 2022) Boulehouache , Soufiane; Mazouzi , Smaine; Ouareth , Selma
    Typically, self-adaptation is achieved by implementing the MAPE-K Control Loop. The researchers agree that multiple control loops should be assigned if the system is complex and large-scale. The hierarchical control has proven to be a good compromise to achieve SAS goals, as there is always some degree of decentralization but it also retains a degree of centralization. The decentralized entities must be coordinated to ensure the consistency of adaptation processes. The high cost of data transfer between coordinating entities may be an obstacle to achieving system scalability. To resolve this problem, coordination should only define between entities that require communication between them. However, most of the current SAS relies on static MAPE-K. In this article, authors present a new method that allows changing the structure and behavior of loops. Authors base on exploration strategies for online reinforcement learning, using the feature model to define the adaptation space.