263 citations · 921 across the 54 of their papers we have counts for
14 papers · 1 filter
Securing Fixed Neural Network Steganography
Zicong Luo, Sheng Li, Guobiao Li +2
Image steganography is the art of concealing secret information in images in a way that is imperceptible to unauthorized parties. Recent advances show that is possible to use a fix…
DRAW: Defending Camera-shooted RAW against Image Manipulation
Xiaoxiao Hu, Qichao Ying, Zhenxing Qian +2
RAW files are the initial measurement of scene radiance widely used in most cameras, and the ubiquitously-used RGB images are converted from RAW data through Image Signal Processin…
RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection
Qichao Ying, Jiaxin Liu, Sheng Li +3
The widespread use of face retouching filters on short-video platforms has raised concerns about the authenticity of digital appearances and the impact of deceptive advertising. To…
Towards Deep Network Steganography: From Networks to Networks
Guobiao Li, Sheng Li, Meiling Li +2
With the widespread applications of the deep neural network (DNN), how to covertly transmit the DNN models in public channels brings us the attention, especially for those trained…
StyleStegan: Leak-free Style Transfer Based on Feature Steganography
Xiujian Liang, Bingshan Liu, Qichao Ying +2
In modern social networks, existing style transfer methods suffer from a serious content leakage issue, which hampers the ability to achieve serial and reversible stylization, ther…
Generative Model Watermarking Suppressing High-Frequency Artifacts
Li Zhang, Yong Liu, Xinpeng Zhang +1
Protecting deep neural networks (DNNs) against intellectual property (IP) infringement has attracted an increasing attention in recent years. Recent advances focus on IP protection…
Decision-based iterative fragile watermarking for model integrity verification
Zhaoxia Yin, Heng Yin, Hang Su +2
Typically, foundation models are hosted on cloud servers to meet the high demand for their services. However, this exposes them to security risks, as attackers can modify them afte…
Generative Steganographic Flow
Ping Wei, Ge Luo, Qi Song +3
Generative steganography (GS) is a new data hiding manner, featuring direct generation of stego media from secret data. Existing GS methods are generally criticized for their poor…
Generative Steganography Diffusion
Ping Wei, Qing Zhou, Zichi Wang +3
Generative steganography (GS) is an emerging technique that generates stego images directly from secret data. Various GS methods based on GANs or Flow have been developed recently.…
Robust image steganography against lossy JPEG compression based on embedding domain selection and adaptive error correction
Xiaolong Duan, Bin Li, Zhaoxia Yin +2
Transmitting images for communication on social networks has become routine, which is helpful for covert communication. The traditional steganography algorithm is unable to success…
Multi-modal Fake News Detection on Social Media via Multi-grained Information Fusion
Yangming Zhou, Yuzhou Yang, Qichao Ying +2
The easy sharing of multimedia content on social media has caused a rapid dissemination of fake news, which threatens society's stability and security. Therefore, fake news detecti…
Steganography of Steganographic Networks
Guobiao Li, Sheng Li, Meiling Li +2
Steganography is a technique for covert communication between two parties. With the rapid development of deep neural networks (DNN), more and more steganographic networks are propo…
Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment
Gongyang Li, Zhi Liu, Xinpeng Zhang +1
Recently, relying on convolutional neural networks (CNNs), many methods for salient object detection in optical remote sensing images (ORSI-SOD) are proposed. However, most methods…
Trojaning semi-supervised learning model via poisoning wild images on the web
Le Feng, Zhenxing Qian, Sheng Li +1
Wild images on the web are vulnerable to backdoor (also called trojan) poisoning, causing machine learning models learned on these images to be injected with backdoors. Most previo…