06- إعلام آلي

Permanent URI for this collectionhttps://dspace.univ-tebessa.dz/handle/123456789/154

Browse

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A Deep Learning Approach for Detecting Distributed Denial of Service Attacks
    (Larbi Tebessi University-Tebessa, 2026-06-02) BOUROUGAA, Khadidja; SOUAHI, Mohamed Salah
    Distributed Denial of Service (DDoS) attacks remain one of the most significant threats to network security. By overwhelming a target with massive amounts of malicious traffic, these attacks disrupt essential online services and cause substantial financial losses. Traditional detection methods, such as signature-based and anomaly-based systems, struggle to detect new and evolving attack patterns. Moreover, most existing deep learning approaches focus on binary classification (normal vs attack), which limits their ability to distinguish between different types of DDoS attacks. This study proposes a deep learning approach for multi-class DDoS attack detection using a one-dimensional Convolutional Neural Network (1D CNN). The proposed model is trained and evaluated on the CICDDoS2019 dataset, which contains various types of DDoS attacks. The dataset undergoes preprocessing steps including label mapping, removal of constant and identifying columns, duplicate removal, handling of missing values, normalization, and type conversion. The model is evaluated using standard metrics: accuracy, precision, recall, and F1-score. The experimental results demonstrate that the 1D CNN model effectively distinguishes be- tween different types of DDoS attacks. The main contributions of this work include a detailed analysis of the CICDDoS2019 dataset, a 1D CNN model for multi-class classification, and a comparison with existing approaches.
  • Thumbnail Image
    Item
    Renforcement adaptatif AES par génération de S-Box basée sur un réseau neuronal
    (Université Echahid Cheikh Larbi Tebessi, 2026-06-07) AOUACHRIA, Rahma; BOULAHBAL, Amani; BENABBES, Sofiane
    Ce mémoire de master traite du renforcement de l'Advanced Encryption Stan- dard (AES) par le remplacement de la S-Box statique par une S-Box dynamique générée à l'aide de réseaux de neurones. L'approche proposée conserve la structure originale de l'AES tout en intégrant un perceptron multicouche (MLP) entraîné de manière supervisée sur la S-Box standard de l'AES, suivi de perturbations gaus- siennes temporaires des poids pour produire des S-Box variables. Les propriétés cryptographiques (non-linéarité, uniformité diérentielle, eet avalanche, bijecti- vité, précision) ainsi que les performances temporelles sont évaluées. Les résultats expérimentaux montrent que la S-Box dynamique basée sur le MLP atteint une non-linéarité de 112, une uniformité diérentielle de 4, un eet avalanche de 0,5049, une bijectivité parfaite et une précision de 93,75