scispace - formally typeset
Search or ask a question
Author

Nenghai Yu

Other affiliations: City University of Hong Kong
Bio: Nenghai Yu is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Steganography & Steganalysis. The author has an hindex of 29, co-authored 299 publications receiving 2974 citations. Previous affiliations of Nenghai Yu include City University of Hong Kong.


Papers
More filters
Proceedings ArticleDOI
20 Jun 2021
TL;DR: In this paper, a multi-attentional deepfake detection network is proposed, which consists of three key components: 1) multiple spatial attention heads to make the network attend to different local parts; 2) textural feature enhancement block to zoom in the subtle artifacts in shallow features; 3) aggregate the low-level textural features and high-level semantic features guided by the attention maps.
Abstract: Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. Recently, how to detect such forgery contents has become a hot research topic and many deepfake detection methods have been proposed. Most of them model deepfake detection as a vanilla binary classification problem, i.e, first use a backbone network to extract a global feature and then feed it into a binary classifier (real/fake). But since the difference between the real and fake images in this task is often subtle and local, we argue this vanilla solution is not optimal. In this paper, we instead formulate deepfake detection as a fine-grained classification problem and propose a new multi-attentional deepfake detection network. Specifically, it consists of three key components: 1) multiple spatial attention heads to make the network attend to different local parts; 2) textural feature enhancement block to zoom in the subtle artifacts in shallow features; 3) aggregate the low-level textural feature and high-level semantic features guided by the attention maps. Moreover, to address the learning difficulty of this network, we further introduce a new regional independence loss and an attention guided data augmentation strategy. Through extensive experiments on different datasets, we demonstrate the superiority of our method over the vanilla binary classifier counterparts, and achieve state-of-the-art performance. The models will be released recently at https://github.com/yoctta/multiple-attention.

242 citations

Journal ArticleDOI
TL;DR: By introducing Healthchain, both IoT data and doctor diagnosis cannot be deleted or tampered with so as to avoid medical disputes, and security analysis and experimental results show that the proposed Healthchain is applicable for smart healthcare system.
Abstract: With the dramatically increasing deployment of the Internet of Things (IoT), remote monitoring of health data to achieve intelligent healthcare has received great attention recently. However, due to the limited computing power and storage capacity of IoT devices, users’ health data are generally stored in a centralized third party, such as the hospital database or cloud, and make users lose control of their health data, which can easily result in privacy leakage and single-point bottleneck. In this paper, we propose Healthchain, a large-scale health data privacy preserving scheme based on blockchain technology, where health data are encrypted to conduct fine-grained access control. Specifically, users can effectively revoke or add authorized doctors by leveraging user transactions for key management. Furthermore, by introducing Healthchain, both IoT data and doctor diagnosis cannot be deleted or tampered with so as to avoid medical disputes. Security analysis and experimental results show that the proposed Healthchain is applicable for smart healthcare system.

226 citations

Proceedings ArticleDOI
02 Mar 2021
TL;DR: Wang et al. as mentioned in this paper proposed a spatial-phase shallow learning (SPSL) method, which combines spatial image and phase spectrum to capture the up-sampling artifacts of face forgery to improve the transferability.
Abstract: The remarkable success in face forgery techniques has received considerable attention in computer vision due to security concerns. We observe that up-sampling is a necessary step of most face forgery techniques, and cumulative up-sampling will result in obvious changes in the frequency domain, especially in the phase spectrum. According to the property of natural images, the phase spectrum preserves abundant frequency components that provide extra information and complement the loss of the amplitude spectrum. To this end, we present a novel Spatial-Phase Shallow Learning (SPSL) method, which combines spatial image and phase spectrum to capture the up-sampling artifacts of face forgery to improve the transferability, for face forgery detection. And we also theoretically analyze the validity of utilizing the phase spectrum. Moreover, we notice that local texture information is more crucial than high-level semantic information for the face forgery detection task. So we reduce the receptive fields by shallowing the network to suppress high-level features and focus on the local region. Extensive experiments show that SPSL can achieve the state-of-the-art performance on cross-datasets evaluation as well as multi-class classification and obtain comparable results on single dataset evaluation.

183 citations

Journal ArticleDOI
TL;DR: A novel framework for RDH-EI based on reversible image transformation (RIT), in which the ciphertexts may attract the notation of the curious cloud and the data-embedding process executed by the cloud server is irrelevant with the processes of both encryption and decryption.
Abstract: With the popularity of outsourcing data to the cloud, it is vital to protect the privacy of data and enable the cloud server to easily manage the data at the same time. Under such demands, reversible data hiding in encrypted images (RDH-EI) attracts more and more researchers’ attention. In this paper, we propose a novel framework for RDH-EI based on reversible image transformation (RIT). Different from all previous encryption-based frameworks, in which the ciphertexts may attract the notation of the curious cloud, RIT-based framework allows the user to transform the content of original image into the content of another target image with the same size. The transformed image, that looks like the target image, is used as the “encrypted image,” and is outsourced to the cloud. Therefore, the cloud server can easily embed data into the “encrypted image” by any RDH methods for plaintext images. And thus a client-free scheme for RDH-EI can be realized, that is, the data-embedding process executed by the cloud server is irrelevant with the processes of both encryption and decryption. Two RDH methods, including traditional RDH scheme and unified embedding and scrambling scheme, are adopted to embed watermark in the encrypted image, which can satisfy different needs on image quality and large embedding capacity, respectively.

114 citations

Proceedings ArticleDOI
01 Oct 2019
TL;DR: A Denoiser and UPsampler Network (DUP-Net) structure as defenses for 3D adversarial point cloud classification, where the two modules reconstruct surface smoothness by dropping or adding points.
Abstract: Neural networks are vulnerable to adversarial examples, which poses a threat to their application in security sensitive systems. We propose a Denoiser and UPsampler Network (DUP-Net) structure as defenses for 3D adversarial point cloud classification, where the two modules reconstruct surface smoothness by dropping or adding points. In this paper, statistical outlier removal (SOR) and a data-driven upsampling network are considered as denoiser and upsampler respectively. Compared with baseline defenses, DUP-Net has three advantages. First, with DUP-Net as a defense, the target model is more robust to white-box adversarial attacks. Second, the statistical outlier removal provides added robustness since it is a non-differentiable denoising operation. Third, the upsampler network can be trained on a small dataset and defends well against adversarial attacks generated from other point cloud datasets. We conduct various experiments to validate that DUP-Net is very effective as defense in practice. Our best defense eliminates 83.8% of C&W and l2 loss based attack (point shifting), 50.0% of C&W and Hausdorff distance loss based attack (point adding) and 9.0% of saliency map based attack (point dropping) under 200 dropped points on PointNet.

110 citations


Cited by
More filters
Journal ArticleDOI

[...]

08 Dec 2001-BMJ
TL;DR: There is, I think, something ethereal about i —the square root of minus one, which seems an odd beast at that time—an intruder hovering on the edge of reality.
Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

33,785 citations

01 Jan 2006

3,012 citations

Reference EntryDOI
15 Oct 2004

2,118 citations

Journal ArticleDOI
01 Jan 1977-Nature
TL;DR: Bergh and P.J.Dean as discussed by the authors proposed a light-emitting diode (LEDD) for light-aware Diodes, which was shown to have promising performance.
Abstract: Light-Emitting Diodes. (Monographs in Electrical and Electronic Engineering.) By A. A. Bergh and P. J. Dean. Pp. viii+591. (Clarendon: Oxford; Oxford University: London, 1976.) £22.

1,560 citations