Andere Kunden interessierten sich auch für
![Named Entity Recognition in Natural languages using Hidden Markov Mode]( "Named Entity Recognition in Natural languages using Hidden Markov Mode")
Named Entity Recognition in Natural languages using Hidden Markov Mode36,99 €![Performance Analysis of Cross Layer Based Virus Detection techniques]( "Performance Analysis of Cross Layer Based Virus Detection techniques")
Performance Analysis of Cross Layer Based Virus Detection techniques32,99 €![DDoS Attack Mitigation Architecture]( "DDoS Attack Mitigation Architecture")
DDoS Attack Mitigation Architecture36,99 €![What a Robot Sees in a Mirror?]( "What a Robot Sees in a Mirror?")
What a Robot Sees in a Mirror?32,99 €![Proper wear of facemask using machine learning to fight Covid 19 virus]( "Proper wear of facemask using machine learning to fight Covid 19 virus")
Proper wear of facemask using machine learning to fight Covid 19 virus29,99 €![Comparative Analysis of Malware Detection Techniques]( "Comparative Analysis of Malware Detection Techniques")
Comparative Analysis of Malware Detection Techniques26,99 €![Malware Propagation and Detection]( "Malware Propagation and Detection")
Malware Propagation and Detection46,99 €
A metamorphic computer virus employs different obfuscation techniques to mutate its code, in its new instance in the new infected file. The mutated instance has the similar behavior and function of the original virus, but the binary pattern of the code is entirely different from its parent. Therefore, metamorphic variants of a virus family cannot be simply detected by most of commercial antivirus products, because their solutions depend on a signature database and employ string signature-based detection methods. Hence, the antivirus detection engine can be evaded by obfuscation techniques, easily. This book is a technical report of a PhD research on the metamorphic computer viruses, their characteristics and features, and detection methods. In this research, a machine learning based model (Hidden Markov Model) has been developed to classify and detect this type of malware. In the proposed method, a HMM is designed and trained on the statistical features of opcodes of executable viral files. This model can be employed to recognize the similar patterns and detect other variants of the same family of metamorphic viruses. The evaluation of the proposed method is discussed in details.