Multi-model cooperative defense method facing deep learning antagonism attack

Abstract

A multi-model cooperative defense method facing deep learning antagonism attack comprises the following steps of: 1) performing unified modeling based on a gradient attack to provide a [Rho]-loss model; 2) according to design of a unified model, for an countering attack of a target model fpre(x), according to a generation result of a countering sample, classifying a basic expression form of an attack into two classes; 3) analyzing the parameters of the model, performing parameter optimization of the [Rho]-loss model and search step length optimization of a disturbance solution model for the countering sample; and 4) for the mystique of a black box attack, designing an experiment based on an adaboost concept, generating a plurality of different types of substitution models, used to achievethe same task, for integration, designing a multi-model cooperative defense method with high defense capability through an attack training generator of an integration model with high defense capability, and providing multi-model cooperative detection attack with weight optimal distribution. The multi-model cooperative defense method is high in safety and can effectively defense the attack of a deep learning model for the antagonism attack.

Description

technical field [0001] The invention belongs to the security field of machine learning methods in the field of artificial intelligence. Aiming at the threat of anti-sample attacks in deep learning methods in current machine learning, a multi-model collaborative defense method is proposed to effectively improve its security. Background technique [0002] Due to its good learning performance, the deep neural network model has been widely used in the real world, including computer vision, natural language processing, bioinformatics analysis, etc. Especially in the field of computer vision, face recognition, automatic driving, etc. have appeared through deep learning models to automatically recognize faces and complete automatic understanding of road signs and other images. Therefore, the popularization and application of deep learning is the key to the successful promotion of face recognition and automatic driving technologies. One of the techniques. [0003] With the continuo...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the deficiencies of the existing adversarial aggregation methods, which have low security and cannot defend against adversarial attacks on deep learning models, the present invention provides a method with high security and effective defense against adversarial attacks on deep learning models. Multi-model collaborative defense method

Images