基于多层激励函数量子神经网络的入侵检测研究

为解决传统入侵检测模型所存在的检测效率低，对未知的入侵行为检测困难等问题，对神经网路隐层激励函数进行了研究，利用多层激励函数的量子神经网络模型进行入侵检测，该量子神经网络借鉴量子理论中量子态叠加的思想，使得隐层神经元能表示更多地状态或量级，从而很好的对入侵类型进行分类，增加隐层神经元的处理速度和检测性能法。实验表明，叠加的每个sigmoid函数较传统的sigmoid函数不仅对已知的入侵具有较好的识别能力，而且能较好的识别未知入侵行为，从而实现入侵检测的智能化。

Study of an intrusion detection based on quantum neural networks technology

The neural network technology obtained the widespread application in the intrusion what most has represents is the BP neural network, but the local minimum nature of itself has limited the detection performance enhancement. In order to solve the problem of low detection rate for novel attacks and the difficulties in detecting unknown intrusions existing in traditional intrusion systems, has been studied the activation function of the hidden layer of neural networks,use multi - layer activation function of quantum neural networks to detect the intrusion, drawing on the quantum theory in the idea of quantum superposition, the hidden layer neurons can be said that the state or order of magnitude more. Experimental results show that Superimposed sigmoid functions has a better detection rate not only to the known intrusion, but also to the unknown intrusion than the conventional sigmoid function, thus realizing an intelligent intrusion detection system.