Physical world confrontation sample generation method and device, electronic equipment and storage medium

Abstract

The invention relates to a physical world confrontation sample generation method and device, electronic equipment and a storage medium, and is applied to the technical field of artificial intelligence. The method comprises the steps: obtaining a target disturbance image which is an image projected to a holographic film and generated based on an adversarial attack algorithm, and obtaining a target image, wherein the target image comprises a target disturbance image and a first face image of the first user, and determining the target image as a target confrontation sample. The anti-disturbance image of the digital world displayed in the electronic equipment can be converted into the real physical world in a holographic imaging mode, the anti-disturbance image does not need to be printed, so that unknown loss introduced in the printing process is avoided, the attack success rate of the physical world anti-disturbance sample is improved, and the global disturbance attack can be realized in the physical world.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a method, device, electronic device and storage medium for generating physical world adversarial samples. Background technique [0002] Adversarial example physical world attack studies the problem of how to construct an adversarial example in the real physical world when deploying a deep learning model in the real physical world. [0003] At present, the public physical world attack methods in the field of adversarial example attack and defense can be divided into local perturbation methods and global perturbation methods. The local perturbation method needs to convert the adversarial perturbation of the digital world into the physical world by printing, and it is easy to introduce unknowns during the conversion process. The loss of the physical world reduces the attack success rate, while the global perturbation of the digital world is difficult to...

AI Technical Summary

Problems solved by technology

[0003] At present, the public physical world attack methods in the field of adversarial example attack and defense can be divided into local perturbation methods and global perturbation methods. The local perturbation method needs to convert the adversarial perturbation of the digital world into the physical world by printing, and it is easy to introduce unknowns during the conversion process. The loss of the physical world reduces the attack success rate, while the global perturbation of the digital world is difficult to achieve in the physical world

Images