International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 09 Issue: 06 | June 2022
p-ISSN: 2395-0072
www.irjet.net
PROVIDING CYBER SECURITY SOLUTION FOR MALWARE DETECTION USING SUPPORT VECTOR MACHINE ALGORITHM (SVM) Narmada B, Arfath Khan M, Mahalakshmi P, Jayasree S Narmada B, Assistant Professor and Head of the Department, Department of Computer Science and Engineering, Dhirajlal Gandhi College of Technology, Salem, Tamil Nadu, India Arfath Khan M, Student, Department of Computer Science and Engineering, Dhirajlal Gandhi College of Technology, Salem, Tamil Nadu, India Mahalakshmi P, Student, Department of Computer Science and Engineering, Dhirajlal Gandhi College of Technology, Salem, Tamil Nadu, India Jayasree S, Student, Department of Computer Science and Engineering, Dhirajlal Gandhi College of Technology, Salem, Tamil Nadu, India ---------------------------------------------------------------------***--------------------------------------------------------------------Abstract – Malware detection developers faced an issue with a generation of recent signatures of malware code. A very famous and recognized technique is the pattern-based malware code detection technique. This results in the evasion of signatures that are built to support the code syntax. During this paper, we discuss some well-known methods of malware detection supported by the semantic feature extraction technique. In the current decade, most of the authors focused on the malware feature extraction process for the generic detection process. The effectiveness of the Malicious Sequence Pattern Matching technique for malware detection invites moderation and improvement of the present system and method. Some authors used the rule mining technique, another used the graph technique and a few also focused on the feature clustering process of malware detection. The focus of the Multi-Classification framework is to detect the malicious affected files. To protect legitimate users from attacks, the foremost significant line of defense against malware is antimalware software products, which mainly use signature-based methods for detection. Machine Learning algorithms are proved useful at identifying zero-day attacks or detecting an unusual behavior of systems that might indicate an attack or malware.
interestingness metrics, complexity considerations, post-processing of discovered structures, visualization, and online updating. Data processing is the analysis step of the "knowledge discovery in databases" process or KDD. 1.2 Cyber Security The cyberattack surface in modern enterprise environments is huge, and it is continuing to grow rapidly. This implies that analyzing and improving an organization’s cybersecurity posture needs over mere human intervention. AI is now becoming essential to information security, as these technologies are capable of swiftly analyzing numerous data sets and tracking down a large sort of cyber threats. These technologies are continually learning and improving, drawing data from past experiences and the present to pinpoint new sorts of attacks that will occur today or tomorrow.
2. EXISTING SYSTEM Due to its damage to Internet security, malware(e.g., virus, worm, Trojan)and its finding has caught the eye of both the anti-malware industry and researchers for many years. To shield genuine users from the attacks, the foremost significant line of defense against malware is anti-malware software products, which mostly use signature-based methods for detection. However, this method fails to acknowledge new, unseen malicious executables. To unravel this problem, during this paper, supported the instruction sequences extracted from the file sample set, we propose a good sequence mining algorithm to get malicious sequential patterns, then J48 classifiers constructed for malware detection supported the discovered patterns. The developed data processing framework composed of the proposed sequential pattern mining method and J48 classifier can well characterize the malicious patterns from the collected file samples to effectively detect newly unseen malware samples.
Key Words: Data Processing, Computer Science, Cyber Security, J48, SVM Algorithm, KDD, Malware Detection
1. INTRODUCTION 1.1 DATA MINING Data mining is an interdisciplinary subfield of engineering science. It’s the computational process of discovering patterns in large data sets involving methods at the intersection of computing, machine learning, statistics, and database systems. The goal of the information mining process is to extract information from an information set and transform it into a lucid structure for further use. Except for the raw analysis step, it involves database and data management aspects, data processing, model and inference considerations,
© 2022, IRJET
|
Impact Factor value: 7.529
|
ISO 9001:2008 Certified Journal
|
Page 128