ANALYSIS OF MALWARE DETECTION TECHNIQUES USING MACHINE LEARNING
Shivakumar Nethani1, Lade Gunakar Rao2, Kusumba Jyoshna Devi3
1Department of Computer Science and Engineering & Hyderabad Institute of Technology and Management, Hyderabad, Telangana, India
2Department of Computer Science and Engineering & SR University, Warangal, Telangana, India
3Department of Computer Science and Applications & Govt Degree College, Warangal, Telangana, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Malicious software that has the potential to infect a single computer or an entire company's network is referred to as malware. One of the most serious threats to online safety at the moment is malware and viruses. Given how quickly the amount of malware is growing, there is a severe threat to global security. All modern malware applications have a tendency to include multiple polymorphic layers or side mechanisms that automatically update themselves at regular intervals in order to avoid detection by any antivirus software and avoid detection for longer periods of time. We provide a modular framework that enables the use of several machine learning techniques, such as decision-tree [1], It has become the hardest job for security vendors to disguise a program as malware. Android malware has advanced to the point where it is increasingly resistant to common detection methods in terms of intelligence and cognition. Machine learning-based strategies have become a significantly more effective technique to deal with the complexity and uniqueness of emerging Android threats. They work by first identifying current malware activity patterns, then using this data to differentiate between known risks and unknown threats [2].
Key Words: Malware, Malware Detection, Machine Learning, Malware Analysis, Android applications, feature extraction, malware detection, Android, co-existence, Android.
