Hybrid Email Spam Detection Method Using Negative Selection and Genetic Algorithms

Abstract: In this paper, a new model was proposed to cope with the trend of email spam that improves the generation of a detector in the improved and standard negative selection algorithm (NSA) with the use of stochastic distribution to model the data point using genetic algorithms. The theoretical analysis and the experimental result show that the performance of proposed method is higher than the improved and standard NSA, which the accuracy of the proposed model is 91.90%, while the improved NSA model is 85.27%, and the standard NSA model is 62.75%.

Keywords: Negative selection algorithm, genetic algorithm, spam email, spam detectors generation.