Title :
A method for HMM-based system calls intrusion detection based on hybrid training algorithm
Author :
Wang, Panhong ; Shi, Liang ; Wang, Beizhan ; Liu, Yangbin ; Wu, Yuanqin
Author_Institution :
Software Sch., Xiamen Univ., Xiamen, China
Abstract :
HMM (Hidden Markov Model) is a very important intrusion detection tool. The classical HMM training algorithm is a climbing algorithm. It can only find a local optimal solution. To improve the accuracy of HMM training, this paper introduces a hybrid algorithm into intrusion detection. Experiments show that this algorithm can find a more accurate model.
Keywords :
computer network security; hidden Markov models; HMM based system calls intrusion detection; climbing algorithm; hidden Markov model; hybrid training algorithm; Algorithm design and analysis; Computational modeling; Data models; Evolutionary computation; Hidden Markov models; Intrusion detection; Training; Anomaly intrusion detection; Evolutionary computation; HMM; System call;
Conference_Titel :
Information and Automation (ICIA), 2011 IEEE International Conference on
Conference_Location :
Shenzhen
Print_ISBN :
978-1-4577-0268-6
Electronic_ISBN :
978-1-4577-0269-3
DOI :
10.1109/ICINFA.2011.5949013
