Targeted attack method for deep hash retrieval and terminal equipment

Abstract

The invention discloses a targeted attack method for deep hash retrieval and terminal equipment, and the method comprises the steps: providing a sample set with a label t, inputting all samples in thesample set into a deep hash retrieval model, and generating a corresponding hash code; obtaining a representative hash code ha by adopting a bit voting algorithm; specifying the size of the hyper-parameter alpha to be 0-1, and designing a loss function; calculating the gradient of x' by using a gradient descent method and updating x' by using the gradient; projecting the generated adversarial sample x' to enable the x' to meet infinite constraints and image space; judging whether a preset updating frequency is reached or not, and if so, obtaining an adversarial sample x'; and inputting the adversarial sample x' into the deep hash retrieval model, and returning a sample of an expected category. When the deep hash retrieval model is designed, the attack method is adopted, the safety and robustness of the model can be improved, and the generated adversarial sample can enable the retrieval model to return to a category sample expected by an attacker.

Description

technical field [0001] The invention relates to the technical field of hash retrieval, in particular to a targeted attack method and terminal equipment for deep hash retrieval. Background technique [0002] Large-scale data approximate nearest neighbor retrieval has the characteristics of high efficiency and high performance, and is used in many search engines to retrieve images or videos, such as Google and Bing. Among these approximate nearest neighbor search methods, hash-based retrieval has received more attention, which can map data to a compact binary space, thereby using Hamming distance to measure similarity and improve computational efficiency. [0003] The hash retrieval method based on deep learning can achieve the best performance in the current hash retrieval. However, many studies have shown that the deep learning model is vulnerable to adversarial attacks, which affects the performance of the deep learning model. According to different attack purposes, advers...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a targeted attack method and terminal equipment for deep hash retrieval in view of the deficiencies of the prior art, aiming at solving the lack of a targeted attack method for deep hash retrieval in the prior art , which is not conducive to the research on the robustness and security of the retrieval system

Images