Adversarial sample generation method, system and apparatus for outlier removal method

Abstract

The invention belongs to the field of image recognition, and specifically relates to an adversarial sample generation method, system and device for outlier removal methods, aiming to solve the problem that the adversarial samples used in the existing deep learning-based classification model training cannot The method of removing outliers makes image classification errors, resulting in the problem of poor robustness and low accuracy of the trained classification model. The present invention includes: obtaining a training data set with a class label, inputting three-dimensional point cloud data into a classification model and calculating a classification loss, respectively calculating the gradient of the classification loss on the three-dimensional point cloud data and the three-dimensional point cloud data on removing outliers The gradient of the two gradients is multiplied by the scaling factor to generate fusion perturbation, and the fusion perturbation is applied to the three-dimensional point cloud data to iteratively generate adversarial samples. The adversarial samples generated by the invention can still cause image classification errors under the condition of removing outliers, which improves the robustness and classification accuracy of the trained model.

Description

technical field [0001] The invention belongs to the field of image recognition, and in particular relates to an adversarial sample generation method, system and device for outlier removal methods. Background technique [0002] The 3D point cloud classification model based on deep learning has been greatly developed in recent years, and it can achieve a classification accuracy of about 90% on the ModelNet40 dataset. But at the same time, in the field of image classification, the classification model based on deep learning is vulnerable to the attack of adversarial samples. From the appearance, the adversarial samples are almost the same as the normal samples, but the adversarial samples will make the classification model make mistakes. However, there are few studies on adversarial examples in the field of 3D point cloud, and the field of 3D point cloud classification is related to engineering projects with high security requirements such as automatic driving and machine grasp...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned problems in the prior art, the existing image classification model based on deep learning adopts conventional adversarial examples for training, which has poor robustness and cannot meet the precise classification requirements in fields with extremely high security requirements. Problem, the present invention provides an adversarial sample generation method for the outlier removal method, the method includes:

Images