Title :
Study on the Dynamic Forensics Method Based on BP Neural Network
Author_Institution :
Dept. of Comput. Sci. & Technol., Hunan Police Acad., Changsha, China
Abstract :
In view that the efficiency of computer forensics technology is insufficient and some other problems at present, a computer dynamic forensics method has been proposed based on BP neural network. This method has combined the advantages of artificial neural network in pattern recognition which can timely and accurately identify the network attack behaviors. On this basis, a prototype system with dynamic forensics has been designed. And the experiment has showed that this system has high detection rate for the network bad behaviors and the detection performance is superior to other pattern recognition methods.
Keywords :
backpropagation; computer forensics; neural nets; pattern recognition; BP neural network; artificial neural network; computer dynamic forensics method; computer forensics technology; network attack behavior; network bad behavior detection; pattern recognition; Artificial neural networks; Computers; Feature extraction; Forensics; Mutual information; Neurons; Training; BP neural network; dynamic forensics; feature extraction; information security;
Conference_Titel :
Future Computer Sciences and Application (ICFCSA), 2011 International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4577-0317-1
DOI :
10.1109/ICFCSA.2011.58
