Adversarial sample generation method based on content-aware GAN

Abstract

The invention discloses an adversarial sample generation method based on content awareness GAN, which changes a training process on the basis of WGAN_GP, directly generates an adversarial sample witha target by inputting random noise, adds a content feature extraction part, restrains the quality of the generated sample under the condition of not influencing an attack effect, and improves the accuracy of adversarial sample generation. Content characteristics of adversarial samples can be kept unchanged as much as possible. The system comprises a generator G, a discriminator D, a target model f, a disturbance evaluation part and a feature extraction network, wherein the generator is responsible for generating a sample from random noise, the generator is trained according to a loss functionof the discriminator D, the target model f, the disturbance evaluation part and the feature extraction network, and the generator directly generates an unlimited adversarial sample from the noise. Onthe basis of the generative adversarial network, the semantic information of the concerned sample and a mode of directly generating the adversarial sample instead of a superimposed disturbance mode, direct generation of the adversarial sample of the specified target is realized by using unsupervised GAN training, the sample generation speed is increased, and the quality of the generated sample isimproved; the change of the adversarial sample in the content feature region is reduced while the high attack success rate is maintained.

Description

technical field [0001] The invention belongs to the field of deep learning, in particular to a method for generating an adversarial example based on content-aware GAN. Background technique [0002] Artificial intelligence is a hot method used to solve problems in various fields in recent years. As one of the fields of machine learning, deep learning has gradually become a research hotspot in the field of computer vision. With the continuous development of deep neural network models, more and more deep learning training frameworks and open source tools have been developed. At the same time, as the performance of hardware such as GPUs used for training continues to improve, the software and hardware conditions for training complex models have become increasingly complex. Increasing availability has greatly advanced the application of deep learning in various fields of real life, and computer vision solutions are gradually entering the fields where safety requirements are criti...

AI Technical Summary

Problems solved by technology

These works are different in the methods of realizing adversarial attacks, but there are more or less problems, such as the quality of the generated adversarial samples is not high, the added perturbation is easy to be recognized, the attack success rate is not high, and the attack mobility inferior

Images