1 code implementation • 23 Feb 2024 • Shuren Qi, Yushu Zhang, Chao Wang, Zhihua Xia, Xiaochun Cao, Jian Weng
Developing robust and interpretable vision systems is a crucial step towards trustworthy artificial intelligence.
no code implementations • 9 Nov 2023 • Jianwei Fei, Zhihua Xia, Benedetta Tondi, Mauro Barni
In recent years, there has been significant growth in the commercial applications of generative models, licensed and distributed by model developers to users, who in turn use them to offer services.
no code implementations • 25 Oct 2023 • Jianwei Fei, Zhihua Xia, Benedetta Tondi, Mauro Barni
We present the results of extensive experiments showing that the presence of the watermark has a negligible impact on the quality of the generated images, and proving the superior robustness of the watermark against model modification and surrogate model attacks.
no code implementations • 29 May 2023 • Junren Qin, Shanxiang Lyu, Fan Yang, Jiarui Deng, Zhihua Xia, Xiaochun Cao
In this paper, we propose a novel RDH-based static DNN watermarking scheme using quantization index modulation (QIM).
1 code implementation • 24 Apr 2023 • Peipeng Yu, Jiahan Chen, Xuan Feng, Zhihua Xia
The powerful ability of ChatGPT has caused widespread concern in the academic community.
no code implementations • 29 Dec 2022 • Jianwei Fei, Yunshu Dai, Huaming Wang, Zhihua Xia
Our goal is to reduce the features that are easy to learn in the training phase, so as to reduce the risk of overfitting on specific forgery types.
no code implementations • 27 Dec 2022 • Huaming Wang, Jianwei Fei, Yunshu Dai, Lingyun Leng, Zhihua Xia
To our knowledge, we are the first to conduct data augmentation in the fingerprint domain.
no code implementations • 14 Nov 2022 • Wenyuan Yang, Shuo Shao, Yue Yang, Xiyao Liu, Ximeng Liu, Zhihua Xia, Gerald Schaefer, Hui Fang
In this paper, we propose a novel client-side FL watermarking scheme to tackle the copyright protection issue in secure FL with HE.
no code implementations • CVPR 2022 • Jianwei Fei, Yunshu Dai, Peipeng Yu, Tianrun Shen, Zhihua Xia, Jian Weng
We also propose a Local Enhancement Module (LEM) to improve the discrimination between local features of real and forged regions, so as to ensure accuracy in calculating anomalies.
no code implementations • 7 Sep 2022 • Jianwei Fei, Zhihua Xia, Benedetta Tondi, Mauro Barni
The aim is to watermark the GAN model so that any image generated by the GAN contains an invisible watermark (signature), whose presence inside the image can be checked at a later stage for ownership verification.
no code implementations • 25 May 2022 • Yong Xu, Zhihua Xia, Zichi Wang, Xinpeng Zhang, Jian Weng
With a stego media discovered, the adversary could find out the sender or receiver and coerce them to disclose the secret message, which we name as coercive attack in this paper.
no code implementations • 10 Mar 2022 • Sulong Ge, Zhihua Xia, Yao Tong, Jian Weng, Jianan Liu
By applying this scheme, when the watermarked image is displayed on the screen and captured by a camera, the watermark can be still extracted from the captured photographs.
no code implementations • 26 Feb 2022 • Sulong Ge, Zhihua Xia, Jianwei Fei, Xingming Sun, Jian Weng
Then the identity can be extracted to prove the copyright from the watermarked carrier even after suffering various attacks.