HRRP target-free 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-free adversarial sample generation method based on deep learning. The method comprises the steps of training a deep neural network model by using a data set, and obtaining parameters thereof; selecting a sample and initializing algorithm parameters; for all sample categories, based on an FGSM algorithm, obtaining a disturbance scaling factor of each category by adopting a binary search method; selecting a minimum scaling factor from the disturbance scaling factors obtained by all the categories, calculating the gradient direction of the category corresponding to the scaling factor, and obtaining target-free fine-grained confrontation disturbance of n samples; adding the target-free fine-grained adversarial disturbance to the original sample to generate an adversarial sample; aggregating the target-free fine-grained adversarial disturbances of the n samples to obtain target-free general disturbances; and adding the target-free general disturbance to any sample to generate an adversarial sample. According to the method, target-free fine-grained disturbance and general disturbance can be obtained, corresponding adversarial samples are generated, and the safety of radar target recognition is improved.

Description

technical field [0001] The invention belongs to the field of radar image recognition, and specifically relates to a method for generating HRRP targetless 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 Lear...

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 destructive to the classification performance of the classifier, indicating that radio signal classification based on deep learning algorithms is very vulnerable

However, whether there are adversarial examples for target recognition based on radar one-dimensional range images is still an open question, and no relevant research literature has been found so far.

Images