Implementing Hashing for Virus Recognition using ANN (HASH-ANN)
Mohamed H. Almeer
Dr. Mohamed H. Almeer, Computer Science and Engineering Department, College of Engineering, Qatar University, Doha.
Manuscript received on 23 May 2015 | Revised Manuscript received on 30 May 2015 | Manuscript published on 30 May 2015 | PP: 31-35 | Volume-4 Issue-2, May 2015 | Retrieval Number: B1409054215©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper, we propose an intelligent first-warning system for virus code detection based on Artificial Neural Networks (ANNs). The proposed system operates in accordance with the basic principles of ANNs to conduct pattern matching of 32-bit hash signatures and detect virus signatures by means of the hashing applied to the byte content of executable code. The proposed system can accurately detect virus code in accordance with information it has learned, and gives false positive ratios within acceptable ranges. The results of experiments conducted show that the combination of 32-bit hashing and neural networks results in a low false positive rate. This paper also discusses the key ideas and approaches, along with the necessary adaptations and adjustments undertaken in the neural network model underlying the proposed early warning virus detection system.
Keyword: Hashing, Hash code, BKDR hash function, ANN, Neural Networks, Virus detection.
Scope of the Article: High Speed Networks