A soft-threshold defense method for remote sensing image adversarial samples

Abstract

The invention discloses a soft threshold defense method for remote sensing image confrontation samples. The correctly classified remote sensing images and the confrontation samples are stored in the same type of verification set, and the remote sensing images that cannot be correctly classified in the verification set are deleted; the original image is used as a positive sample, Use the adversarial samples as negative samples to reclassify the images in the saved validation set; combine the classification output confidences to get a new dataset; train a logistic regression model on the new dataset; obtain the decision boundary from the original images and the adversarial samples Threshold of output confidence; compare the output confidence of the current input image with the defensive soft threshold to determine whether the current input image is an adversarial sample. The invention can effectively defend against the attack of adversarial samples in the problem of remote sensing image scene classification, and the fooling rate of the convolutional neural network is reduced to 0.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image classification, and in particular relates to a soft threshold defense method of remote sensing image confrontation samples. [0002] technical background [0003] Convolutional neural network (CNN) has excellent feature extraction ability and high accuracy, and has become a general technique for object recognition in the field of remote sensing. It is widely used in remote sensing fields such as disaster management, forest monitoring and urban planning. Well-performing CNNs can have high financial benefits. However, many studies have shown that CNNs are very vulnerable to adversarial samples, which are carefully generated and imperceptible, which can make the model predict wrong results with high confidence. Adversarial examples have become the most concerned security issue for CNNs in practical applications. Adversarial examples demonstrate the vulnerability of convolutional neural...

AI Technical Summary

Problems solved by technology

However, these algorithms require model retraining and are computationally intensive

The second is to detect only

Images