Machine Learning Approaches to Cyber Security

Cyber-security is used to identify cyber-attacks while they are acting on a computer or network\ud system to compromise security of the system. We discuss the concept of Hidden Markov Model\ud with the Large Deviation Theory approaches because now a days statistical anomaly detection with\ud Large Deviation theory approach have been used to find attack signatures in network traffic. We\ud present two different approaches to characterize traffic: a model-free approach and a model-based\ud approach. Model free approach is method of types based approach using Sanov’s theorem whereas\ud model based approach is HMM based approach uses Large deviation theory. We discuss how these\ud theories can be applied for anomaly detection from network traffic. We study their effectiveness in\ud anomaly detection. We will discuss how much these statistical methods affective on spatio-temporal\ud traffic data. We also discuss about how length of traffic data affect our Markov model. How our\ud estimated model is related with true but unknown model