Document Details

Document Type : Article In Conference 
Document Title :
Data Mining Methods for Malware Detection using Instruction Sequences
استخراج البيانات عن طرق الكشف عن البرامج الضارة باستخدام التعليمات متواليات
 
Subject : Data mining, malware detection, instruction sequences 
Document Language : English 
Abstract : Malicious programs pose a serious threat to computer security. Traditional approaches using signatures to detect malicious programs pose little danger to new and unseen programs whose signatures are not available. The focus of the research is shifting from using signature patterns to identify a specific malicious program and/or its variants to discover the general malicious behavior in the programs. This paper presents a novel idea of automatically identifying critical instruction sequences that can classify between malicious and clean programs using data mining techniques. Based upon general statistics gathered from these instruction sequences we formulated the problem as a binary classification problem and built logistic regression, neural networks and decision tree models. Our approach showed 98.4% detection rate on new programs whose data was not used in the model building process. 
Conference Name : International Conference on Artificial Intelligence and Applications 
Duration : From : 11/2/1429 AH - To : 13/2/1429 AH
From : 11/2/2008 AD - To : 13/2/2008 AD 
Publishing Year : 1429 AH
2008 AD 
Number Of Pages : 5 
Article Type : Article 
Conference Place : Austria 
Organizing Body : AIA 
Added Date : Wednesday, February 16, 2011 

Researchers

Researcher Name (Arabic)Researcher Name (English)Researcher TypeDr GradeEmail
معظم صديقيSiddiqui, Muazzam ResearcherDoctoratemaasiddiqui@kau.edu.sa

Files

File NameTypeDescription
 29006.docx docx 

Back To Researches Page