6GCVAE: Gated Convolutional Variational Autoencoder for IPv6 Target Generation

TL;DR

This paper introduces 6GCVAE, a deep learning-based model using gated convolutional layers within a Variational Autoencoder framework to generate IPv6 target addresses more effectively for network scanning.

Contribution

The paper proposes a novel gated convolutional VAE model for IPv6 address generation, incorporating address classification methods to enhance performance.

Findings

6GCVAE outperforms traditional VAE models

It surpasses existing target generation algorithms

Effective learning of IPv6 address structure

Abstract

IPv6 scanning has always been a challenge for researchers in the field of network measurement. Due to the considerable IPv6 address space, while recent network speed and computational power have been improved, using a brute-force approach to probe the entire network space of IPv6 is almost impossible. Systems are required an algorithmic approach to generate more possible active target candidate sets to probe. In this paper, we first try to use deep learning to design such IPv6 target generation algorithms. The model effectively learns the address structure by stacking the gated convolutional layer to construct Variational Autoencoder (VAE). We also introduce two address classification methods to improve the model effect of the target generation. Experiments indicate that our approach 6GCVAE outperformed the conventional VAE models and the state-of-the-art target generation algorithm in two active address datasets.