本文主要研究网络不良信息识别方法,提出了一种基于免疫原理的不良信息识别方法,其中应用了多层防护、抗原识别、阴性选择、克隆选择、协同刺激及免疫应答等免疫原理,并对检测规则生成方法进行了改进。通过实验验证了该方法在识别率、误判率与漏判率方面都优于传统的不良信息识别方法,并具有良好的适用性和扩展性。 In this paper, we mainly study the method of identifying bad network information, and propose a method of identifying bad information based on immune principle, in which immune principles such as multilayer protection, antigen recognition, negative selection, clonal selection, costimulation and immune response are applied. Rules generation method has been improved. The experimental results show that this method is better than the traditional method of identifying bad information in recognition rate, false positive rate and missed judgment rate, and has good applicability and expansibility.