A Generic Perturbation Generation Method Based on Generative Adversarial Networks

Abstract

The invention discloses a method for generating general disturbances based on generative confrontation networks. First, the generation network generates general disturbances to obtain confrontation samples; then the discriminative network distinguishes the confrontational samples from the original samples, and calculates the discriminant network objective function and backpropagates for optimization; finally The deep learning model predicts the classification of adversarial samples, and the discriminative network distinguishes the adversarial samples, and calculates and generates the network objective function and optimizes it by backpropagation; the general disturbance generation method based on GAN provided by the present invention can be used in the fields of computer vision and deep learning for Users provide ideas for machine learning model security research.

Description

technical field [0001] The invention belongs to the technical field of deep learning, and in particular relates to a general disturbance generation method in a black-box scenario based on a generative confrontation network. Background technique [0002] In 2012, in the ImageNet large-scale visual recognition challenge, Deep Neural Networks (DNNs) achieved the best image classification results at that time, and began to gain widespread attention from the industry. In recent years, with the improvement of big data technology and computing performance, deep learning has developed rapidly, and more and more applications in real life have begun to use deep learning model applications. For example, autonomous driving technology uses deep learning to complete object detection, reinforcement learning, multimodal learning, etc.; Apple uses deep learning to complete biometric authentication technology based on facial recognition; behavior-based malware detection uses deep learning to ...

AI Technical Summary

Problems solved by technology

The current general perturbation generation methods require the attacker to have white-box access to the model, but in real scenarios, the attacker is often limited in authority and can only access the final output value of the deep learning model

Images