Immune Cooperation Mechanism-Based Learning Framework

Inspired from the immune cooperation (IC) mechanism in biological immune systems (BIS), this chapter presents an IC mechanism-based learning (ICL) framework. In this framework, a sample is expressed as an antigen-specific feature vector and an antigen-nonspecific feature vector, simulating the antigenic determinant and danger features in the BIS. The ICL framework simulates the BIS in the view of immune signals and takes full advantage of the cooperation effect of the immune signals, which improves the performance of the ICL framework. The ICL-MD model involves two modules, feature extraction and classification. In the malware detection problem, malware are taken as antigens, while benign programs are non-antigens. In order to ensure that the experimental results are reliable and the proposed ICL-MD model outperforms the GC-MD and LC-MD approaches statistically, an analysis of variance (ANOVA) was done followed by two t hypothesis tests (t-test). Comprehensive experimental results demonstrate that the ICL framework is an effective learning framework.