神经网络应用在入侵检测领域中,可以处理不完整输入信息,同时能够识别新的入侵行为,并行计算和存储特性能够在更短时间内发现入侵行为.为了进一步提高单个神经网络在入侵检测系统中的检测性能,提出了基于模糊积分的多神经网络融合模型MNNF模型.采用KDD99作为实验数据,实验结果表明,MNNF模型具有较好的入侵检测性能.
[1] 蒋建春, 马恒太, 任党恩, 卿斯汉, JIANG Jian-chun, MA Heng-tai, REN Dan-gen, QING Si-han. 网络安全入侵检测:研究综述 [J]. 软件学报 2000.
[2] 唐正军, 李建华. 入侵检测技术 [M]. 北京:清华大学出版社 2004.
[3] DEBAR H, DORIZZI B. An application of a recurrent network to an intrusion detection system [M]. New York 1992.
[4] TAN K. The application of neural networks to UNIX computer security [A]. Perth, Australia 1995.
[5] HONLUND, ALBERT. A UNIX anomaly detection system using self-organizing maps [A]. LOUVAIN-La-Neuve, Belgium 1998.
[6] GHOSH A, SCHWARTZBARD A, SCHATZ A. Learning program behavior profiles for intrusion detection [A]. Washington, DC 1999.
[7] CANNADY J, MAHAFFEY J. The application of artificial neural networks to misuse detection:initial results [J/OL]. http://www.raid-symposium.org/raid98/ProgRAID98/Talks.html 2006.
[8] LIPPMANN RP, CUNNINGHAM R K. Improving intrusion detetion performance using keyword selection and neural networks [J]. Computer Networks-the International Journal of Computer and Tetecommunicaions Networking 2000, 34(04).
[9] WENKE LEE, SAVATORE J. A framework for constructing features and models for intrusion detection systems [J]. ACM Transactions on Information and System Security 2000, 3(04).
[10] RICHARD M D, LIPPMANN R P. Neural network classifier estimate Bayesian a posteriori probabilitiea [J]. Neural Computation 1991, 3(04).
[11] 杜布瓦 D, 普哈德 H, 江苏省模糊数学专业委员会. 模糊集与模糊系统-理论和应用 [M]. 南京:江苏科学技术出版社 1987.
[12] Sung-Bae Cho, Kim J.H.. Combining multiple neural networks by fuzzy integral for robust classification [J]. IEEE transactions on systems, man, and cybernetics 1995, 2(2).
[13] Sung-Bae Cho, Kim J.H.. Multiple network fusion using fuzzy logic [J]. IEEE Transactions on Neural Networks 1995, 2(2).
