Virus-Evolutionary Genetic Algorithm Based Selective Ensemble for Steganalysis

Traditional classifiers in steganalysis are no longer applicable when faced with massive feature set and high-dimensional sample set. We proposed a kind of selective ensemble classifier for universal steganalysis based on virus-evolutionary genetic algorithm. After generating some base learners, we selected some of them according to genetic optimization with an additonal virus population. The final detection results came from weighted voting. Experiments showed that proposed selective ensemble classifier performed better than existing ones.