首页|Identifying Distributed Denial of Service Attacks through Multi-Model Deep Learning Fusion and Combinatorial Analysis

Identifying Distributed Denial of Service Attacks through Multi-Model Deep Learning Fusion and Combinatorial Analysis

扫码查看
原文链接
  • NETL
  • NSTL
  • Springer Nature
Distributed Denial of Service (DDoS) attacks pose a major threat to organizations by overwhelming their networks and servers. Effective identification of DDoS attacks is crucial for timely mitigation. This paper proposes a novel approach using deep learning and Combinatorial Fusion Analysis (CFA) for improved DDoS attack identification. Four deep neural network models are developed for binary classifica-tion of network traffic as either legitimate or DDoS attack. The models utilize differ-ent input features extracted from network traffic data to learn complex patterns. To enhance performance, the probabilistic outputs from the four models are fused using CFA. This combinatorial approach effectively aggregates the models' predictions to improve attack detection accuracy. Extensive experiments on real network data dem-onstrate that the proposed combinatorial fusion of multiple deep learning models achieves higher precision compared to individual models and other ensemble tech-niques. The results highlight the benefits of combining diverse deep learning models with combinatorial fusion for robust and accurate identification of DDoS attacks. This approach provides an effective solution to the growing threat of DDoS attacks.

ClassificationCombinatorial fusion analysisDDoSDeep learningSecurity

Ali Alfatemi、Mohamed Rahouti、D. Frank Hsu、Christina Schweikert、Nasir Ghani、Aiman Solyman、Mohammad I. Saryuddin Assaqty

展开 >

Computer and Information Science, Fordham University, Bronx, NY 10458, USA

CSMS Division, St. John's University, Queens 11439, NY, USA

Electrical Engineering Department, University of South Florida, Tampa, FL, USA

Computer Science and Technology, University of Milan, Milan, Italy

ECS Faculty, Universitas Nahdlatul Ulama Indonesia, Jakarta 10320, Indonesia

展开 >

2025

10.1007/s10922-024-09882-0

Journal of network and systems management

Journal of network and systems management

SCI
ISSN：1064-7570
年,卷(期)：2025.33(1)
  • 65