IPv6 active address detection method and device based on reinforcement learning

Abstract

The invention provides an IPv6 active address detection method and device based on reinforcement learning, and the method comprises the steps: obtaining an IPv6 seed address, and determining a plurality of high-density regions of the seed address; performing iterative detection on each high-density area through a pre-trained multi-arm tiger machine model, including: generating a preset number of target addresses in each high-density area, and detecting whether each target address is an active address; determining the number of active addresses and the number of inactive addresses in the preset number of target addresses, updating the expected rewards of the corresponding high-density areas according to the number of the active addresses and the number of the inactive addresses, repeatedly executing the above steps, with each high-density area being subjected to iterative detection, so that the target addresses are obtained; and converging the density distribution of the seed addresses to the density distribution of the active addresses. According to the method, the density distribution of the seed addresses moves towards the actual active address distribution, so that the high-density area of the active addresses can be determined in the network, and the efficiency of detecting the active addresses is improved.

Description

technical field [0001] The present application relates to the technical field of computer networks, in particular to a method and device for detecting IPv6 active addresses based on reinforcement learning. Background technique [0002] At present, when detecting active IPv6 addresses in the target area, if there are enough seed addresses in the target area, the target address generation algorithm based on the seed addresses can usually be used to detect active IPv6 addresses. Assuming that the seed sampling distribution of active addresses in the target area is uniform, the density distribution of seed addresses is consistent with the density distribution of actual active addresses in this area. The higher the density of seed addresses in the target area, the higher the probability of detecting active addresses. Therefore, we expect to find the high-density area of ​​the seed address and perform address detection in the high-density area, so as to achieve the purpose of dete...

AI Technical Summary

Problems solved by technology

[0003] However, due to the sampling deviation of seed addresses and other factors, the density distribution of seed addresses may not be consistent with the density distribution of actual active addresses in the target area, resulting in the address detection method in the related art. The density of many actual active addresses is low address detection in the area, which reduces the detection efficiency and wastes detection resources

Images