Integrated Bayes Network and Hidden Markov Model for Host based IDS
Nagaraju Devarakonda, Srinivasulu Pamidi, V. Valli Kumari, Aliseri Govardhan · International Journal of Computer Applications · 2012
Today Internet is more popular for many users and business applications such as banking, social networks, education, entertainment, scientific research, and recently cloud computing. The number of services provided by the internet service providers through Internet is rapidly increasing. For many applications security has become a serious issue for anyone connected to the Internet. Security should be provided by the ISPs to the Internet users in the form confidentiality, integrity, and authentication. These can be provided through IDS. In our paper we have proposed a simple, easy and efficient approach for building IDS using integrated model of Bayes Net with Hidden Markov Model. The first phase of the model is to build the Bayesian network using the dataset. Once the network is built the conditional probability or joint probability for each node can be determined. The Bayes network has been used as state transition diagram for HMM. The HMM parameters can be estimated using the Bayesian Network. We have used a standard kddcup99 dataset for building the model. This model can be able to differentiate the intruders from normal users with low false positive rate and high true positive rate. The model works for even high dimensional data streams with high performance detection rate and robust to noise.