Unmanned aerial vehicle attack prediction method and system based on bidirectional long-short-term memory model

Abstract

The invention discloses an unmanned aerial vehicle attack prediction method and system based on a bidirectional long-short-term memory model, and the method comprises the steps: constructing the bidirectional long-short-term memory model which comprises a forward memory model and a backward memory model, and carrying out the bidirectional training of the bidirectional long-short-term memory model through employing a log index; predicting a log index of the attack sequence vector according to the trained bidirectional long-short-term memory model, respectively outputting a forward prediction result and a backward prediction result of h time steps by the forward memory model and the backward memory model, and calculating an average probability of each output label in the forward prediction result and the backward prediction result, and sorting the probabilities according to a descending order, and taking the log index with the maximum probability as an abnormal point positioning prediction result.

Description

technical field [0001] The invention belongs to the field of network security, and in particular relates to a method and system for predicting an unmanned aerial vehicle attack based on a bidirectional long short-term memory model, which can be used in the safety protection of an unmanned aerial vehicle system. Background technique [0002] UAVs have entered people's lives from the military field to the industrial field, and have also played an important role in the civilian field. They have brought a lot to production and life in the fields of cruise, monitoring, aerial photography, agriculture, express delivery, power inspection and emergency rescue. Come convenient. Due to these mission requirements, drones need to collect, process, and transmit large amounts of sensitive data, making drones an interesting target for attackers. UAVs are widely used in occasions involving national security, important property, etc., and contain important national secrets. In recent years,...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a system based on the confidentiality, sensitivity, volatility, and difficulty of protection of UAV system data, the extremely high importance of its information and the urgent need for information security of UAV system A UAV attack prediction method based on a two-way long-short-term memory model to solve the above-mentioned deficiencies in existing technologies and ensure the security of verification information

Images