597 citations · 2.3k across the 106 of their papers we have counts for
13 papers · 1 filter
Real-Time Anomaly Detection With HMOF Feature
Huihui Zhu, Bin Liu, Guojun Yin +3
Anomaly detection is a challenging problem in intelligent video surveillance. Most existing methods are computation consuming, which cannot satisfy the real-time requirement. In th…
DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense
Hang Zhou, Kejiang Chen, Weiming Zhang +3
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-Ne…
CAAD 2018: Iterative Ensemble Adversarial Attack
Jiayang Liu, Weiming Zhang, Nenghai Yu
Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible…
Emerging Applications of Reversible Data Hiding
Dongdong Hou, Weiming Zhang, Jiayang Liu +3
Reversible data hiding (RDH) is one special type of information hiding, by which the host sequence as well as the embedded data can be both restored from the marked sequence withou…
CAAD 2018: Powerful None-Access Black-Box Attack Based on Adversarial Transformation Network
Xiaoyi Dong, Weiming Zhang, Nenghai Yu
In this paper, we propose an improvement of Adversarial Transformation Networks(ATN) to generate adversarial examples, which can fool white-box models and black-box models with a s…
Distribution-Preserving Steganography Based on Text-to-Speech Generative Models
Kejiang Chen, Hang Zhou, Hanqing Zhao +3
Steganography is the art and science of hiding secret messages in public communication so that the presence of the secret messages cannot be detected. There are two distribution-pr…
Capacity Control of ReLU Neural Networks by Basis-path Norm
Shuxin Zheng, Qi Meng, Huishuai Zhang +3
Recently, path norm was proposed as a new capacity measure for neural networks with Rectified Linear Unit (ReLU) activation function, which takes the rescaling-invariant property o…
Decouple Learning for Parameterized Image Operators
Qingnan Fan, Dongdong Chen, Lu Yuan +3
Many different deep networks have been used to approximate, accelerate or improve traditional image operators, such as image smoothing, super-resolution and denoising. Among these…
Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition
Guojun Yin, Lu Sheng, Bin Liu +4
Recognizing visual relationships <subject-predicate-object> among any pair of localized objects is pivotal for image understanding. Previous studies have shown remarkable progress…
Detection based Defense against Adversarial Examples from the Steganalysis Point of View
Jiayang Liu, Weiming Zhang, Yiwei Zhang +4
Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible…
Stereoscopic Neural Style Transfer
Dongdong Chen, Lu Yuan, Jing Liao +2
This paper presents the first attempt at stereoscopic neural style transfer, which responds to the emerging demand for 3D movies or AR/VR. We start with a careful examination of ap…
-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
Qi Meng, Shuxin Zheng, Huishuai Zhang +3
It is well known that neural networks with rectified linear units (ReLU) activation functions are positively scale-invariant. Conventional algorithms like stochastic gradient desce…
IREXF: Data Exfiltration from Air-gapped Networks by Infrared Remote Control Signals
Zheng Zhou, Weiming Zhang, Nenghai Yu
he technology on infrared remote control is widely applied in human daily life. It is also applied in the place with a top security level. Infrared remote control signal is regarde…