Shuang Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shuang Wu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Bo Li
Vivo Mobile Communication Co., Ltd
4 shared publications - Guodong Mu
Youtu Laboratory, Tencent, Shanghai, China
2 shared publications - Shice Liu
Youtu Laboratory, Tencent, Shanghai, China
2 shared publications Shouhong Ding
Youtu Laboratory, Tencent, Shanghai, China
2 shared publications- Shouhong Ding
Tencent Youtu Lab, Shanghai, China
2 shared publications - Wenqiang Zhang
Fudan University, Shanghai, China
2 shared publications
Latest Publications
- 28 October 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 331
Exploring the adversarial robustness of face forgery detection with decision-based black-box attacks
- 28 October 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 331
Exploring the adversarial robustness of face forgery detection with decision-based black-box attacks
- 25 August 2025
- Published by Elsevier in Neurocomputing
- Vol. 655
EnfoMax: Domain entropy and mutual information maximization for domain generalized face anti-spoofing
- 25 August 2025
- Published by Elsevier in Neurocomputing
- Vol. 655
EnfoMax: Domain entropy and mutual information maximization for domain generalized face anti-spoofing
- 28 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 4058-4069
MFAE: Masked Frequency Autoencoders for Domain Generalization Face Anti-Spoofing
The generalizable face anti-spoofing (FAS) has attracted much attention recently. Even though many existing methods perform well under intra-domain settings, the model’s performance in the unseen domain is not satisfying. In this paper, we shift our attention to the frequency domain to seek a solution. Specifically, we examine the characteristics of different frequency band components of FAS images and observe that the model’s cross-domain performance is very sensitive to low-frequency features. To alleviate this sensitivity and improve the model’s performance in FAS cross-domain tasks, we propose a new approach called Masked Frequency Autoencoders (MFAE). MFAE randomly masks a portion of frequencies on the low-frequency spectrum of the image and then reconstructs the image from the resulting embedding. This innovative Masked Image Modeling (MIM) strategy can be used as a self-supervised task for pre-training vision transformers (ViTs), which can reduce the ViT encoder’s sensitivity to domain shifts. Additionally, we add an auxiliary content-regularization decoder in our MFAE to encourage the encoder to be insensitive to low-frequency features. The results show that the model insensitive to low-frequency features performs well on extensive public datasets and outperforms other state-of-the-art methods in cross-domain FAS tasks.
- 28 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 4058-4069
MFAE: Masked Frequency Autoencoders for Domain Generalization Face Anti-Spoofing
The generalizable face anti-spoofing (FAS) has attracted much attention recently. Even though many existing methods perform well under intra-domain settings, the model’s performance in the unseen domain is not satisfying. In this paper, we shift our attention to the frequency domain to seek a solution. Specifically, we examine the characteristics of different frequency band components of FAS images and observe that the model’s cross-domain performance is very sensitive to low-frequency features. To alleviate this sensitivity and improve the model’s performance in FAS cross-domain tasks, we propose a new approach called Masked Frequency Autoencoders (MFAE). MFAE randomly masks a portion of frequencies on the low-frequency spectrum of the image and then reconstructs the image from the resulting embedding. This innovative Masked Image Modeling (MIM) strategy can be used as a self-supervised task for pre-training vision transformers (ViTs), which can reduce the ViT encoder’s sensitivity to domain shifts. Additionally, we add an auxiliary content-regularization decoder in our MFAE to encourage the encoder to be insensitive to low-frequency features. The results show that the model insensitive to low-frequency features performs well on extensive public datasets and outperforms other state-of-the-art methods in cross-domain FAS tasks.
- 23 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 5522-5536
Query-Efficient Decision-Based Black-Box Patch Attack
Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible adversarial perturbations. As a complementary type of adversary, patch attacks that introduce perceptible perturbations to the images have attracted the interest of researchers. Existing patch attacks rely on the architecture of the model or the probabilities of predictions and perform poorly in the decision-based setting, which can still construct a perturbation with the minimal information exposed – the top-1 predicted label. In this work, we first explore the decision-based patch attack. To enhance the attack efficiency, we model the patches using paired key-points and use targeted images as the initialization of patches, and parameter optimizations are all performed on the integer domain. Then, we propose a differential evolutionary algorithm named DevoPatch for query-efficient decision-based patch attacks. Experiments demonstrate that DevoPatch outperforms the state-of-the-art black-box patch attacks in terms of patch area and attack success rate within a given query budget on image classification and face verification. Additionally, we conduct the vulnerability evaluation of ViT and MLP on image classification in the decision-based patch attack setting for the first time. Using DevoPatch, we can evaluate the robustness of models to black-box patch attacks. We believe this method could inspire the design and deployment of robust vision models based on various DNN architectures in the future.
- 23 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 5522-5536
Query-Efficient Decision-Based Black-Box Patch Attack
Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible adversarial perturbations. As a complementary type of adversary, patch attacks that introduce perceptible perturbations to the images have attracted the interest of researchers. Existing patch attacks rely on the architecture of the model or the probabilities of predictions and perform poorly in the decision-based setting, which can still construct a perturbation with the minimal information exposed – the top-1 predicted label. In this work, we first explore the decision-based patch attack. To enhance the attack efficiency, we model the patches using paired key-points and use targeted images as the initialization of patches, and parameter optimizations are all performed on the integer domain. Then, we propose a differential evolutionary algorithm named DevoPatch for query-efficient decision-based patch attacks. Experiments demonstrate that DevoPatch outperforms the state-of-the-art black-box patch attacks in terms of patch area and attack success rate within a given query budget on image classification and face verification. Additionally, we conduct the vulnerability evaluation of ViT and MLP on image classification in the decision-based patch attack setting for the first time. Using DevoPatch, we can evaluate the robustness of models to black-box patch attacks. We believe this method could inspire the design and deployment of robust vision models based on various DNN architectures in the future.
- 6 January 2021
- Published by MyJove Corporation in Journal of Visualized Experiments
- No. 167
Visualizing the Calcitonin Gene-Related Peptide Immunoreactive Innervation of the Rat Cranial Dura Mater with Immunofluorescence and Neural Tracing
Here we present a protocol to visualize spatial correlation of calcitonin gene-related peptide (CGRP)-immunoreactive nerve fibers and blood vessels in the cranial dura mater using immunofluorescence and fluorescent histochemistry with CGRP and phalloidin, respectively. In addition, the origin of these nerve fibers was retrograde traced with a fluorescent neural tracer.
- 6 January 2021
- Published by MyJove Corporation in Journal of Visualized Experiments
- No. 167
Visualizing the Calcitonin Gene-Related Peptide Immunoreactive Innervation of the Rat Cranial Dura Mater with Immunofluorescence and Neural Tracing
Here we present a protocol to visualize spatial correlation of calcitonin gene-related peptide (CGRP)-immunoreactive nerve fibers and blood vessels in the cranial dura mater using immunofluorescence and fluorescent histochemistry with CGRP and phalloidin, respectively. In addition, the origin of these nerve fibers was retrograde traced with a fluorescent neural tracer.