Access the full text.
Sign up today, get DeepDyve free for 14 days.
Qiubin Lin, W. Cao, Zhiquan He, Zhihai He (2021)
Mask Cross-Modal Hashing NetworksIEEE Transactions on Multimedia, 23
Chao Li, Haoteng Tang, Cheng Deng, L. Zhan, Wei Liu (2020)
Vulnerability vs. Reliability: Disentangled Adversarial Examples for Cross-Modal LearningProceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova (2019)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Cong Bai, Chao Zeng, Qing Ma, Jinglin Zhang, Shengyong Chen (2020)
Deep Adversarial Discrete Hashing for Cross-Modal RetrievalProceedings of the 2020 International Conference on Multimedia Retrieval
Tat-Seng Chua, Jinhui Tang, Richang Hong, Haojie Li, Zhiping Luo, Yantao Zheng (2009)
NUS-WIDE: a real-world web image database from National University of Singapore
O. Ronneberger, P. Fischer, T. Brox (2015)
U-Net: Convolutional Networks for Biomedical Image SegmentationArXiv, abs/1505.04597
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, D. Erhan, I. Goodfellow, R. Fergus (2013)
Intriguing properties of neural networksCoRR, abs/1312.6199
A. Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu (2017)
Towards Deep Learning Models Resistant to Adversarial AttacksArXiv, abs/1706.06083
Y. Xiao, Cong Wang, Xing Gao (2020)
Evade Deep Image Retrieval by Stashing Private Images in the Hash Space2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
M. Huiskes, M. Lew (2008)
The MIR flickr retrieval evaluation
Giorgos Tolias, Filip Radenovic, Ondřej Chum (2019)
Targeted Mismatch Adversarial Attack: Query With a Flower to Retrieve the Tower2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Weibin Wu, Yuxin Su, Xixian Chen, Shenglin Zhao, Irwin King, Michael Lyu, Yu-Wing Tai (2020)
Boosting the Transferability of Adversarial Samples via Attention2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Yue Cao, Mingsheng Long, Bin Liu, Jianmin Wang (2018)
Deep Cauchy Hashing for Hamming Space Retrieval2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Rong-Cheng Tu, Xian-Ling Mao, Bingchan Ma, Yong Hu, T. Yan, Wei Wei, Heyan Huang (2019)
Deep Cross-Modal Hashing With Hashing Functions and Unified Hash Codes Jointly LearningIEEE Transactions on Knowledge and Data Engineering, 34
Song Liu, Shengsheng Qian, Yang Guan, Jiawei Zhan, Long Ying (2020)
Joint-modal Distribution-based Similarity Hashing for Large-scale Unsupervised Deep Cross-modal RetrievalProceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
Qing-Yuan Jiang, Wu-Jun Li (2016)
Deep Cross-Modal Hashing2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
[ (2020)
Vulnerability vsreliability: Disentangled adversarial examples for cross-modal learning. In Proceedings of the International Conference on Knowledge Discovery & Data Mining
Shengshan Hu, Yechao Zhang, Xiaogeng Liu, L. Zhang, Minghui Li, Hai Jin (2021)
AdvHash: Set-to-set Targeted Attack on Deep Hashing with One Single Adversarial PatchProceedings of the 29th ACM International Conference on Multimedia
Maosen Li, Cheng Deng, Tengjiao Li, Junchi Yan, Xinbo Gao, Heng Huang (2020)
Towards Transferable Targeted Attack2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Jingdong Wang, Ting Zhang, Jingkuan Song, N. Sebe, Heng Shen (2016)
A Survey on Learning to HashIEEE Transactions on Pattern Analysis and Machine Intelligence, 40
Xunguang Wang, Zheng Zhang, Baoyuan Wu, Fumin Shen, Guangming Lu (2021)
Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Xiaodan Li, Jinfeng Li, Yuefeng Chen, Shaokai Ye, Yuan He, Shuhui Wang, Hang Su, Hui Xue (2021)
QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Jiancheng Yang, Yangzhou Jiang, Xiaoyang Huang, Bingbing Ni, Chenglong Zhao (2020)
Learning Black-Box Attackers with Transferable Priors and Query FeedbackArXiv, abs/2010.11742
Chen Ma, L. Chen, Junhai Yong (2020)
MetaSimulator: Simulating Unknown Target Models for Query-Efficient Black-box AttacksArXiv, abs/2009.00960
Ken Chatfield, K. Simonyan, A. Vedaldi, Andrew Zisserman (2014)
Return of the Devil in the Details: Delving Deep into Convolutional NetsArXiv, abs/1405.3531
Chao Li, Shangqian Gao, Cheng Deng, Wei Liu, Heng Huang (2021)
Adversarial Attack on Deep Cross-Modal Hamming Retrieval2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Hui Cui, Lei Zhu, Jingjing Li, Yang Yang, Liqiang Nie (2020)
Scalable Deep Hashing for Large-Scale Social Image RetrievalIEEE Transactions on Image Processing, 29
Alexey Kurakin, I. Goodfellow, Samy Bengio (2016)
Adversarial examples in the physical worldArXiv, abs/1607.02533
Yanru Xiao, Cong Wang (2021)
You See What I Want You to See: Exploring Targeted Black-Box Transferability Attack for Hash-based Image Retrieval Systems2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
I. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio (2014)
Generative adversarial networksCommunications of the ACM, 63
Guoping Zhao, Mingyu Zhang, Jiajun Liu, Yaxian Li, Ji-rong Wen (2020)
AP-GAN: Adversarial patch attack on content-based image retrieval systemsGeoInformatica, 26
Evan Shelhamer, Jonathan Long, Trevor Darrell (2014)
Fully convolutional networks for semantic segmentation2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Wieland Brendel, Jonas Rauber, M. Bethge (2017)
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning ModelsArXiv, abs/1712.04248
Parminder Kaur, H. Pannu, A. Malhi (2021)
Comparative analysis on cross-modal information retrieval: A reviewComput. Sci. Rev., 39
Chaowei Xiao, Bo Li, Jun-Yan Zhu, Warren He, M. Liu, D. Song (2018)
Generating Adversarial Examples with Adversarial NetworksArXiv, abs/1801.02610
X. Lu, Lei Zhu, Zhiyong Cheng, Liqiang Nie, Huaxiang Zhang (2019)
Online Multi-modal Hashing with Dynamic Query-adaptionProceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval
Mingyang Chen, Junda Lu, Yi Wang, Jianbin Qin, Wen Wang (2021)
DAIR: A Query-Efficient Decision-based Attack on Image Retrieval SystemsProceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval
Junda Lu, Mingyang Chen, Yifang Sun, Wei Wang, Yi Wang, Xiaochun Yang (2021)
A Smart Adversarial Attack on Deep Hashing Based Image RetrievalProceedings of the 2021 International Conference on Multimedia Retrieval
Xiaobo Shen, Fumin Shen, Quansen Sun, Yang Yang, Yunhao Yuan, Heng Shen (2017)
Semi-Paired Discrete Hashing: Learning Latent Hash Codes for Semi-Paired Cross-View RetrievalIEEE Transactions on Cybernetics, 47
Jianbo Chen, Michael Jordan (2019)
HopSkipJumpAttack: A Query-Efficient Decision-Based Attack2020 IEEE Symposium on Security and Privacy (SP)
Pengfei Zhang, Yang Li, Zi Huang, Xin-Shun Xu (2021)
Aggregation-Based Graph Convolutional Hashing for Unsupervised Cross-Modal RetrievalIEEE Transactions on Multimedia, 24
Diederik Kingma, Jimmy Ba (2014)
Adam: A Method for Stochastic OptimizationCoRR, abs/1412.6980
Xiaobo Shen, Guohua Dong, Yuhui Zheng, L. Lan, I. Tsang, Quansen Sun (2021)
Deep Co-Image-Label Hashing for Multi-Label Image RetrievalIEEE Transactions on Multimedia, 24
Jiawang Bai, B. Chen, Yiming Li, Dongxian Wu, Weiwei Guo, Shutao Xia, E. Yang (2020)
Targeted Attack for Deep Hashing based RetrievalArXiv, abs/2004.07955
I. Goodfellow, Jonathon Shlens, Christian Szegedy (2014)
Explaining and Harnessing Adversarial ExamplesCoRR, abs/1412.6572
Ruiqing Xu, Chao Li, Junchi Yan, Cheng Deng, Xianglong Liu (2019)
Graph Convolutional Network Hashing for Cross-Modal Retrieval
Tsung-Yi Lin, M. Maire, Serge Belongie, James Hays, P. Perona, Deva Ramanan, Piotr Dollár, C. Zitnick (2014)
Microsoft COCO: Common Objects in Context
Mingyi Zhou, Jing Wu, Y. Liu, Shuaicheng Liu, Ce Zhu (2020)
DaST: Data-Free Substitute Training for Adversarial Attacks2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Yantao Lu, Yunhan Jia, Jianyu Wang, Bai Li, Weiheng Chai, L. Carin, Senem Velipasalar (2019)
Enhancing Cross-Task Black-Box Transferability of Adversarial Examples With Dispersion Reduction2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Erkun Yang, Tongliang Liu, Cheng Deng, D. Tao (2020)
Adversarial Examples for Hamming Space SearchIEEE Transactions on Cybernetics, 50
Chao Li, Shangqian Gao, Cheng Deng, De Xie, Wei Liu (2019)
Cross-Modal Learning with Adversarial Samples
Jun Yu, Hao Zhou, Yibing Zhan, D. Tao (2021)
Deep Graph-neighbor Coherence Preserving Network for Unsupervised Cross-modal Hashing
Gengshen Wu, Zijia Lin, J. Han, Li Liu, Guiguang Ding, Baochang Zhang, Jialie Shen (2018)
Unsupervised Deep Hashing via Binary Latent Factor Models for Large-scale Cross-modal Retrieval
Nathan Inkawhich, W. Wen, Hai Li, Yiran Chen (2019)
Feature Space Perturbations Yield More Transferable Adversarial Examples2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Yujia Liu, Seyed-Mohsen Moosavi-Dezfooli, P. Frossard (2019)
A Geometry-Inspired Decision-Based Attack2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Erkun Yang, Cheng Deng, W. Liu, Xianglong Liu, D. Tao, Xinbo Gao (2017)
Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval
[ (2021)
Simulating unknown target models for query-efficient black-box attacksProceedings of the IEEE Conference on Computer Vision and Pattern Recognition
De Xie, Cheng Deng, Chao Li, Xianglong Liu, D. Tao (2020)
Multi-Task Consistency-Preserving Adversarial Hashing for Cross-Modal RetrievalIEEE Transactions on Image Processing, 29
[ (2014)
Generative adversarial netsAdv. Neural Inf. Process. Syst, 27
Zhuoran Liu, Zhengyu Zhao, M. Larson (2019)
Who's Afraid of Adversarial Queries?: The Impact of Image Modifications on Content-based Image RetrievalProceedings of the 2019 on International Conference on Multimedia Retrieval
Jie Li, R. Ji, Hong Liu, Xiaopeng Hong, Yue Gao, Q. Tian (2018)
Universal Perturbation Attack Against Image Retrieval2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Cheng Deng, Zhaojia Chen, Xianglong Liu, Xinbo Gao, D. Tao (2018)
Triplet-Based Deep Hashing Network for Cross-Modal RetrievalIEEE Transactions on Image Processing, 27
Shupeng Su, Zhisheng Zhong, Chao Zhang (2019)
Deep Joint-Semantics Reconstructing Hashing for Large-Scale Unsupervised Cross-Modal Retrieval2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Deep cross-modal hashing retrieval models inherit the vulnerability of deep neural networks. They are vulnerable to adversarial attacks, especially for the form of subtle perturbations to the inputs. Although many adversarial attack methods have been proposed to handle the robustness of hashing retrieval models, they still suffer from two problems: (1) Most of them are based on the white-box settings, which is usually unrealistic in practical application. (2) Iterative optimization for the generation of adversarial examples in them results in heavy computation. To address these problems, we propose an Efficient Query-based Black-Box Attack (EQB2A) against deep cross-modal hashing retrieval, which can efficiently generate adversarial examples for the black-box attack. Specifically, by sending a few query requests to the attacked retrieval system, the cross-modal retrieval model stealing is performed based on the neighbor relationship between the retrieved results and the query, thus obtaining the knockoffs to substitute the attacked system. A multi-modal knockoffs-driven adversarial generation is proposed to achieve efficient adversarial example generation. While the entire network training converges, EQB2A can efficiently generate adversarial examples by forward-propagation with only given benign images. Experiments show that EQB2A achieves superior attacking performance under the black-box setting.
ACM Transactions on Information Systems (TOIS) – Association for Computing Machinery
Published: Feb 7, 2023
Keywords: Adversarial attack
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.