IPv6 address discovery method and device based on gated convolutional variational auto-encoder

Abstract

The invention relates to an IPv6 address discovery method and device based on a gated convolution variational auto-encoder. The method comprises the following steps: constructing a variation auto-encoder by utilizing a gated convolution layer to obtain a gated convolution variation auto-encoder; training a gating convolution variation auto-encoder, learning distribution of input addresses throughthe encoder in the training process, then sampling latent vectors and reconstructing new address representation through a decoder; The method comprises the steps: using a trained decoder as a generator to generate the predicted active IPv6 addresses in batches; constructing a variational auto-encoder by using the gated convolutional network, so that the potential relationship between address bitscan be discovered while attention is paid to an address importance mark. The invention provides two address classification methods, namely a manual classification method and an unsupervised clusteringmethod, so that the model effect can be effectively improved; compared with the prior art, more active targets can be generated under the limited data set.

Description

technical field [0001] The invention belongs to the field of network technology, and in particular relates to a method and device for discovering an IPv6 address based on a gated convolutional variational autoencoder. Background technique [0002] In network measurement tasks, in order to discover active hosts in the network and judge their activity status, researchers usually use network scanning methods to actively detect all hosts existing in network space. The system confirms that a host is alive by sending a request packet and waiting until a response packet is received from the host. However, IPv6 includes a rather large address space. Current scanners such as Zmap and Masscan cannot scan the entire IPv6 network space. [0003] The state-of-the-art approach to solve this problem is to use IPv6 object generation techniques. The technique takes a set of active IPv6 seed addresses as input and learns the structure of the seed addresses to generate a set of likely activ...

AI Technical Summary

Problems solved by technology

[0007] The present invention uses deep neural network for the first time to solve the problem of IPv6 address generation, that is, the problem of IPv6 address discovery (the generated IPv6 address is the discovered IPv6 address)

Images