Open Access Open Access  Restricted Access Subscription Access

Hybrid Intrusion Detection System for DDoS Attacks


Affiliations
1 Department of Electronics and Communication Engineering, Istanbul Technical University, 34469 Istanbul, Turkey
 

Distributed denial-of-service (DDoS) attacks are one of the major threats and possibly the hardest security problem for today's Internet. In this paper we propose a hybrid detection system, referred to as hybrid intrusion detection system (H-IDS), for detection of DDoS attacks. Our proposed detection system makes use of both anomaly-based and signature-based detection methods separately but in an integrated fashion and combines the outcomes of both detectors to enhance the overall detection accuracy. We apply two distinct datasets to our proposed system in order to test the detection performance of H-IDS and conclude that the proposed hybrid system gives better results than the systems based on nonhybrid detection.
User
Notifications
Font Size

Abstract Views: 48

PDF Views: 0




  • Hybrid Intrusion Detection System for DDoS Attacks

Abstract Views: 48  |  PDF Views: 0

Authors

Ozge Cepheli
Department of Electronics and Communication Engineering, Istanbul Technical University, 34469 Istanbul, Turkey
Saliha Buyukcorak
Department of Electronics and Communication Engineering, Istanbul Technical University, 34469 Istanbul, Turkey
Gunes Karabulut Kurt
Department of Electronics and Communication Engineering, Istanbul Technical University, 34469 Istanbul, Turkey

Abstract


Distributed denial-of-service (DDoS) attacks are one of the major threats and possibly the hardest security problem for today's Internet. In this paper we propose a hybrid detection system, referred to as hybrid intrusion detection system (H-IDS), for detection of DDoS attacks. Our proposed detection system makes use of both anomaly-based and signature-based detection methods separately but in an integrated fashion and combines the outcomes of both detectors to enhance the overall detection accuracy. We apply two distinct datasets to our proposed system in order to test the detection performance of H-IDS and conclude that the proposed hybrid system gives better results than the systems based on nonhybrid detection.