Dual-branch autoencoder network for attacking deep hashing image retrieval models

Due to its powerful representation learning capabilities and efficient computing capabilities, deep learning-based hashing (deep hashing) methods are widely used in large-scale image retrieval. However, there are less studies on the security of deep hashing models. A dual-branch autoencoder network...

Full description

Saved in:
Bibliographic Details
Published in:Dianxin Kexue Vol. 39; no. 11; pp. 96 - 106
Main Authors: Fu, Sizheng, Cao, Chunjie, Liu, Zhiyuan, Tao, Fangjian, Sun, Jingzhang
Format: Journal Article
Language:Chinese
Published: Bejing China International Book Trading 01.11.2023
Beijing Xintong Media Co., Ltd
Subjects:
adversarial attack
deep hashing
Deep learning
image retrieval
Perturbation
Retrieval
targeted attack
ISSN:1000-0801
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Due to its powerful representation learning capabilities and efficient computing capabilities, deep learning-based hashing (deep hashing) methods are widely used in large-scale image retrieval. However, there are less studies on the security of deep hashing models. A dual-branch autoencoder network (DBAE) to study targeted attacks on such retrieval was proposed. The main goal of DBAE was to generate imperceptible adversarial samples as query images in order to make the images retrieved by the deep hashing model semantically irrelevant to the original image and relevant to the target image. Numerous experiments demonstrate that DBAE can successfully generate adversarial samples with small perturbations to mislead deep hashing models, and it also verifies the transferability of these perturbations under various settings.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1000-0801