Classification Algorithms of Trojan Horse Detection Based on Behavior

Current anti-Trojan is almost signature-based strategies, which cannot detect new one. Behavior analysis, with the ability to detect Trojans with unknown signatures, is a technique of initiative defense. However, current behavior analysis based anti-Trojan strategies have the following problems: high false or failure alarm rate, poor efficiency, and poor user-friendly interface design, etc. The paper works on the design of an anti-Trojan oriented algorithm based on behavior analysis. And we construct a standard of anti-Trojan algorithm system and point the up-limit of the precision. We propose an improved hierarchical fuzzy classification algorithm which is specifically designed for anti-Trojan. Finally, we organize the experiment to get the results. The results show high classification accuracy using our algorithm. Compared to Bayesian algorithm, our algorithm have better performance.