Application of genetic optimized artificial immune system and neural networks in spam detection

摘要: Spam is a serious universal problem which causes problems for almost all computer users. This issue not only affects normal users of the internet, but also big companies and organizations since it costs huge amount money in lost productivity, wasting users' time network bandwidth. There are many studies on spam indicates that billions dollars yearly. work presents lot modification machine learning method inspired by human immune system called artificial (AIS) new emerging still needs more investigations demonstrations. Core modifications were applied standard AIS with aid Genetic Algorithm (GA). Also Artificial Neural Network (ANN) detection manner. SpamAssassin corpus used our simulations. In several user defined parameters such as culling old lymphocytes. optimized to present instead using value. Also, idea check antibodies introduced. would make able accept types messages previously considered spam. The accomplished introducing we call ''rebuild time''. Moreover, an adaptive weighting lymphocytes modify selection opportunities different gene fragments. this also, core ANN neurons applied; these allow be changed over replacing useless layers. approach Continuous Learning Approach Network, CLA_ANN. final results compared analyzed. Results show both systems, GA ANN, achieved promising scores comparable other known methods.