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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Dianxin Kexue Jg. 39; H. 11; S. 96 - 106
Hauptverfasser: Fu, Sizheng, Cao, Chunjie, Liu, Zhiyuan, Tao, Fangjian, Sun, Jingzhang
Format: Journal Article
Sprache:Chinesisch
Veröffentlicht: Bejing China International Book Trading 01.11.2023
Beijing Xintong Media Co., Ltd
Schlagworte:
adversarial attack
deep hashing
Deep learning
image retrieval
Perturbation
Retrieval
targeted attack
ISSN:1000-0801
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1000-0801