Black box adversarial sample generation method based on low-inquiry image data

Abstract

The invention discloses a black box adversarial sample generation method based on low-inquiry image data, belongs to the technical field of adversarial sample generation methods, and solves the problem of many iterations of an existing obtained effective black box adversarial sample. The method comprises the steps of obtaining current image data in an image recognition application; randomly selecting any known model, setting white box adversarial sample generation parameters based on the known model, and generating an effective white box adversarial sample of the known model based on a white box generation method and the current image data; subtracting the current image data from the white box adversarial sample, and performing normalization operation to generate an adversarial vector; andrespectively sending the current image data and the current image data added with theadversarial vector into an unknown model, updating the current image data by using an ADAM algorithm after obtaining output, obtaining a black box adversarial sample if the requirements are met after updating, and repeatedly executing the updated image data if the requirements are not met. The method is used forgenerating the black box adversarial sample.

Description

technical field [0001] A black-box adversarial sample generation method based on low query image data is used for generating black-box adversarial samples, and belongs to the technical field of adversarial sample generation methods. Background technique [0002] In recent years, artificial intelligence technology represented by deep learning has developed rapidly and has been widely used in various fields. Unmanned and intelligent is bound to be an important trend in the future. At the same time, deep learning is also facing serious reliability problems. Recent studies have found that artificial intelligence algorithms represented by deep learning may be attacked maliciously, whether in the experimental environment or in the real physical world. Today, with the increasing application of artificial intelligence, the threat of security vulnerabilities is becoming increasingly severe. Therefore, the security of artificial intelligence algorithms is a key issue to be solved in...

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned research problems, the purpose of the present invention is to provide a method for generating black-box adversarial samples based on low-inquiry image data, which solves the problem of many iterations and low success rate of effective black-box adversarial samples in the prior art

Images