Behavioral Analysis of Malware using Machine Learning
Arjun Sharma (~arjun42) |
With the recent increase in malicious attacks via ransomware and the losses incurred by various segments of the society, both in terms of data and money, the need of the hour is to find novel techniques to improve detection rates and performance. Current antivirus techniques rely on hash or signature comparisons via static analysis, which makes zero-day detection impossible. In order to cope with this many antivirus companies are now incorporating behavioral approaches.
This talk is going to be about how machine learning can be combined with behavioral analysis in order to cluster the malware samples into distinct similar-behavior families which can further facilitate a paradigm shift in detection techniques. We’ll be focussing on the following areas:
- Introduction to behavioral analysis.
- Its benefits as compared to static approach
- Using behavioral analysis results to generate data
- Using this data to develop our machine learning model
Basics of machine learning
Anushtha Kalia and Arjun Sharma are juniors at Cluster Innovation Centre, which is a department under University of Delhi, pursuing B.Tech in IT and Mathematical Innovations. They both are data science and python enthusiasts and have worked on multiple problems involving the use of various machine learning techniques.