Designing a new model to detect Trojan Horse based on knowledge discovery and data mining

Trojan has become a real threat to computer users for more than a decade. It is considered as one of the most serious threats in cyber world. Trojan has polymorphism characteristics that make the detection processes much harder than before. Therefore, in this thesis a new model called Efficient Troj...

Full description

Saved in:
Bibliographic Details
Main Author: Areej Mustafa Khlaif Abuzaid
Format: Thesis
Language:English
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Trojan has become a real threat to computer users for more than a decade. It is considered as one of the most serious threats in cyber world. Trojan has polymorphism characteristics that make the detection processes much harder than before. Therefore, in this thesis a new model called Efficient Trojan Detection Model (ETDMo) is built to detect Trojan horse more efficiently than before. The novelty of the ETDMo model lies in the method implemented which consists of EDTMo KDD processes and ETDMo trojan classification. On top of that, the static, dynamic and automated (sandbox) analyses also were integrated in this research. The knowledge discovery techniques (KDD) is used for modeling the ETDMo model and the data mining algorithms were used to optimise the performance result. This ETDMo model produces an overall accuracy rate of 98.2% with 1.7% for false positive rate. This result shows a better accuracy rate compared to existing work for malware detection. Other researchers can used this result as their comparison study for their future work.