Unknown threat detection method based on artificial immune thought

Abstract

The invention discloses an unknown threat detection method based on an artificial immune thought, which is used for effectively detecting known and unknown threats. A pre-classification module introduces a convolutional neural network to solve the problems of pre-collection of a self set and pre-classification of network traffic in detection; a negative selection module introduces a gene bank to solve the random generation problem of an initial detector and the specific immunity problem for unknown threats, and introduces hierarchical clustering to improve the training efficiency of the detector; a cloning variation module is used for solving the overlapping detection problem of a high-affinity detector by introducing a detector optimization algorithm based on a genetic algorithm; meanwhile, an LRU-based memory detector fading mechanism is introduced, so that the storage space is effectively released, and the detection efficiency is improved; and an mRNA vaccination module introduces an mRNA vaccine algorithm based on feature importance sorting, decomposes the detected unknown threats according to gene importance and injects the unknown threats into a gene bank, and generates a corresponding detector to realize specific immunization of the unknown threats and variants thereof.

Description

technical field [0001] The invention relates to the technical field of intrusion detection, in particular to an unknown threat detection method based on the idea of ​​artificial immunity. Background technique [0002] The biological immune system has the characteristics of diversity, tolerance, self-organization, and self-adaptation. Artificial immunity is a kind of mathematical model that draws on the ideas of the biological immune system. By defining the morphological space, defining self and non-self, and calculating the structure of affinity The cell model uses a negative selection algorithm to simulate the maturation process of immune cells in the bone marrow, eliminating those immune cells that can match the body, and then the remaining immune cells reach a mature state, and detect threats through these mature immune cells. [0003] The traditional model based on artificial immunity: First, artificially construct the Self set, and then randomly generate immature detect...

AI Technical Summary

Problems solved by technology

[0009] Aiming at the above problems, the present invention proposes an unknown threat detection method based on the idea of ​​artificial immunity, which solves the self-adaptive problem of the Self set by introducing a pre-classification module, solves the detector generation efficiency problem by The detector optimization algorithm of the genetic algorithm solves the problem of large-area overlap in the detector recognition space, and introduces the mRNA vaccine injection module to solve the specific immunity problem of unknown threats

Images