Malicious software detection method and system based on memristor neural network

Abstract

The invention belongs to the technical field of information security, and particularly relates to a malicious software detection method and system based on a memristor neural network. The method comprises the following steps: visualizing to-be-detected software into an RGB color image; carrying out normalization processing on the RGB color image, and storing the RGB color image in a memristor cross array by using a memristor; and extracting image features from the memristor by using the trained neural network model, and carrying out classification and identification. Malicious software is visualized into a color picture, and the image is stored and processed by using the memristor cross array, so that the recognition accuracy is effectively improved, and the generalization ability of the model is improved; the memristor and the lightweight convolutional neural network are combined to realize a memristor neural network solution in an embeddable device, a high-density integrated network is realized based on the memristor, a cross array structure is utilized to enhance information processing capability and expand storage space, a new solution is provided for solving the von Noiemann bottleneck problem, and malicious software detection of the Internet of Things is effectively realized.

Description

technical field [0001] The invention belongs to the technical field of information security, and in particular relates to a malware detection method and system based on a memristive neural network. Background technique [0002] With the rapid development of network technology, the era of Internet of Everything is quietly coming. At the same time that large-scale devices are connected to the Internet, the amount of malware has also experienced a blowout growth. The emergence of malware has become a major problem that is urgently solved today. Early malware detection was mostly based on signature-based methods, but this traditional method relies too much on expert experience and has certain limitations. Currently, research on malware detection based on neural networks is growing explosively. The computational efficiency of neural networks depends partly on computer performance, but most current computers still have a von Neumann bottleneck, that is, after the memory capacit...

AI Technical Summary

Problems solved by technology

The computational efficiency of neural networks depends partly on computer performance, but most current computers still have von Neumann bottlenecks, that is, after the exponential increase in memory capacity, the bottleneck of data transmission bandwidth between CPU and memory

Images