HRRP targeted adversarial sample generation method based on deep learning

Abstract

The invention belongs to the field of radar image recognition, and relates to an HRRP target adversarial sample generation method based on deep learning. The method comprises the following steps: selecting a sample as an original sample and initializing parameters of an algorithm; based on an FGSM algorithm, calculating disturbance and updating the sample by adopting an iterative method, and stopping iteration when the model identifies the adversarial sample as a target category; removing original sample data from the adversarial sample to obtain target disturbance of the selected sample; continuing iteration, stopping iteration when the confidence coefficient of the model to the target category is increased to an expected value, and obtaining an updated adversarial sample; removing original sample data from the adversarial sample to obtain disturbance; scaling the disturbance to be equal to the given general disturbance power to obtain target general disturbance; and adding the general disturbance to any sample to generate an adversarial sample. According to the method, under one-dimensional radar range profile target recognition based on deep learning, a target confrontation sample is generated, and help is provided for improving radar target recognition safety.

Description

technical field [0001] The invention belongs to the field of radar image recognition, and specifically relates to a method for generating HRRP targeted confrontation samples based on deep learning. Background technique [0002] The radar target recognition algorithm based on deep learning has the advantages of end-to-end feature learning, which can effectively improve the target recognition rate and become an important method for radar target recognition. However, recent studies have shown that deep learning-based optical image recognition methods are vulnerable to adversarial attacks from adversarial examples. The existence of adversarial examples shows that deep learning methods have great security risks. [0003] The end-to-end and automatic feature learning advantages of deep learning provide a class of methods for HRRP-based object recognition, which have achieved good results in practical applications. For example, Jarmo Lunden et al. published the paper "Deep Learni...

AI Technical Summary

Problems solved by technology

For example, in radio propagation, Meysam et al. published the paper "Adversarial attacks on deep-learning based radio signal classification" in the journal IEEE Wireless Communications Letters in 2018, and proposed a method for generating white-box and general-purpose black-box adversarial samples, proving that the adversarial The samples are very d...

Images