¹East China University of Science and Technology, Shanghai, China
²Shanghai University of Electric Power, Shanghai, China

---

Abstract—The network anomaly detection technology based on support vector machine (SVM) can efficiently detect unknown attacks or variants of known attacks, however, it cannot be used for detection of large-scale intrusion scenarios due to the demand of computational time. The graphics processing unit (GPU) has the characteristics of multi-threads and powerful parallel processing capability. Based on the system structure and parallel computation framework of GPU, a parallel algorithm of SVM, named GSVM, is proposed. Extensive experiments were carried out onKDD99 and other large-scale datasets, the results showed that GSVM significantly improves the efficiency of intrusion detection, while retaining detection performance.

Index Terms—Network Intrusion Detection, Support Vector Machine, GPU, Parallel Algorithm

[PDF]

Cite: Xueqin Zhang, Yifeng Zhang, Chunhua Gu, "GPU Implementation of Parallel Support Vector Machine Algorithm with Applications to Intruder Detection," Journal of Computers vol. 9, no. 5, pp. 1117-1124, 2014.