Manoj Dahal

Work place: Novell IDC, Bagmane Tech Park, C V Ramannagar, Bangalore, India



Research Interests: Computational Learning Theory


Dr. Manoj Dahal is currently working at Novell, India and his professional works mostly lie on File Access Protocol areas. He received the Ph.D degree on Networking from Tezpur University, India in 2008 for his thesis on Addressing Transport Layer Congestion Control Issues. He is also associated with research on Detection of Botnets using Machine Learning at Sikkim Manipal Institute of Technology, Sikkim, India. He has around 15 years experience in Software Industry. He was a Post-Doctoral Fellow for about a year with INRIA, France at LIP Labs, ENS de Lyon, where he has worked on Traffic Engineering for Optical Networks before working as a Professor for a short period with Sikkim Manipal Institute of Technology, Sikkim. Manoj also worked with Nokia (via Satyam) on routing devices and National Informatics Centre on e-Governance Projects in India before joining Novell.

Author Articles
An Efficient Machine Learning Based Classification Scheme for Detecting Distributed Command & Control Traffic of P2P Botnets

By Pijush Barthakur Manoj Dahal Mrinal Kanti Ghose

DOI:, Pub. Date: 8 Oct. 2013

Biggest internet security threat is the rise of Botnets having modular and flexible structures. The combined power of thousands of remotely controlled computers increases the speed and severity of attacks. In this paper, we provide a comparative analysis of machine-learning based classification of botnet command & control(C&C) traffic for proactive detection of Peer-to-Peer (P2P) botnets. We combine some of selected botnet C&C traffic flow features with that of carefully selected botnet behavioral characteristic features for better classification using machine learning algorithms. Our simulation results show that our method is very effective having very good test accuracy and very little training time. We compare the performances of Decision Tree (C4.5), Bayesian Network and Linear Support Vector Machines using performance metrics like accuracy, sensitivity, positive predictive value(PPV) and F-Measure. We also provide a comparative analysis of our predictive models using AUC (area under ROC curve). Finally, we propose a rule induction algorithm from original C4.5 algorithm of Quinlan. Our proposed algorithm produces better accuracy than the original decision tree classifier.

[...] Read more.
Other Articles