Li Li

Dr. Li Li

School of Communication and Information Engineering, Shanghai University, Shanghai, China
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 July 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
ZYZihan Yuan
Zihan Yuan
Li LiLi Li
Li Li
Zichi WangZichi Wang
Zichi Wang
XZXinpeng Zhang
Xinpeng Zhang
In the scenario of text data and image data interact of the Internet of Things (IoT) applications, the problem of copyright protection of the text-to-image models is threatened due to the replicability and portability of the neural network model. In order to solve this problem, we propose a model watermarking for the typical text-to-image diffusion models (DMs)–stable DMs (SDMs), which is a key aspect of the copyright protection of text-to-image models. Our scheme injects watermark into an SDM and makes the SDM generate watermark through a predefined prompt. The ownership of the SDM can be proved by the different output results of the model to the predefined prompt. The proposed method does not require raw training data and internal details of SDMs, which only need a predefined prompt and watermark to fine tune the pretrained SDM with minimal epoch. A large number of experiments show that our watermarking technology is effective, and can realize the copyright protection of the SDMs on the premise of less influence on the original function.

27 May 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
DWDeyang Wu
Deyang Wu
XZXinpeng Zhang
Xinpeng Zhang
JWJiayan Wang
Jiayan Wang
Li LiLi Li
Li Li
GFGuorui Feng
Guorui Feng
Video watermarking based on frequency domain is proved to have good invisibility and robustness. However, most of the existing video watermarking schemes embed watermarks in the frequency domain based on subblock segmentation, while ignoring the variation relationship between video space and frequency domain features. Therefore, it is difficult to achieve robust authentication in complex application scenarios. In this paper, a ring subband is constructed in DT-CWT domain as the watermark embedding region by analyzing the relationship between video space and frequency domain characteristics under multiple attacks. Subsequently, the double watermark is embedded by modifying the DCT coefficient of the ring subband, with the copyright watermark alternately and repeatedly embedded within the ring subband, and the synchronous watermark is embedded in the outermost concentric circle. In addition, visual encryption (VC) and piecewise linear chaotic mapping (PLCM) methods are used to encrypt the watermark before it is embedded in the concentric rings, and two shared images are generated, one for the watermark embedding stage and the other for the watermark extraction stage. Experimental results demonstrate that the proposed scheme can resist common attacks, such as noise, JPEG compression, rotation, scaling, time synchronization attacks, and its robustness surpasses existing discrete wavelet transform (DWT) and DT-CWT based video watermarking schemes under complex attack scenarios.

25 January 2023 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
Li LiLi Li
Li Li
WZWeiming Zhang
Weiming Zhang
MBMauro Barni
Mauro Barni
Existing methods for Deep Neural Networks (DNN) watermarking either require accessing the internal parameters of the DNN models (white-box watermarking), or rely on backdooring to enforce a desired behavior of the model when the DNN is fed with a specific set of key input images (black-box watermarking). In this paper, we propose a black-box multi-bit DNN watermarking algorithm, suitable for multiclass classification networks, whereby the presence of the watermark can be retrieved from the output of the network in correspondence to any input. To read the watermark, we first apply a power function to the softmax output of the DNN model to map it from an impulse-like to a smooth distibution. Then, we extract the watermark bits by projecting the output of the DNN onto a pseudorandom key vector. Watermark embedding is achieved by adding a proper regularizer term to the training loss. The effectiveness of the proposed method is demonstrated by applying it to various network architectures working on different datasets. The experimental results demonstrate the possibility to embed a robust watermark into the output of the host DNN with a negligible impact on the accuracy of the original task.

19 February 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
Li LiLi Li
Li Li
XZXinpeng Zhang
Xinpeng Zhang
KCKejiang Chen
Kejiang Chen
GFGuorui Feng
Guorui Feng
DWDeyang Wu
Deyang Wu
WZWeiming Zhang
Weiming Zhang
Traditional image steganography conceals secret messages in unprocessed natural images by modifying the pixel value, causing the obtained stego to be different from the original image in terms of the statistical distribution; thereby, it can be detected by a well-trained classifier for steganalysis. To ensure the steganography is imperceptible and in line with the trend of art images produced by Artificial-Intelligence-Generated Content (AIGC) becoming popular on social networks, this paper proposes to embed hidden information throughout the process of the generation of an art-style image by designing an image-style-transformation neural network with a steganography function. The proposed scheme takes a content image, an art-style image, and messages to be embedded as inputs, processing them with an encoder–decoder model, and finally, generates a styled image containing the secret messages at the same time. An adversarial training technique was applied to enhance the imperceptibility of the generated art-style stego image from plain-style-transferred images. The lack of the original cover image makes it difficult for the opponent learning steganalyzer to identify the stego. The proposed approach can successfully withstand existing steganalysis techniques and attain the embedding capacity of three bits per pixel for a color image, according to the experimental results.

16 February 2025 in Mathematics
Verified
Journal Article
Open access
PDF file
HLHuixin Luo
Huixin Luo
Li LiLi Li
Li Li
Juncheng LiJuncheng Li
Juncheng Li
The rapid advancement of AI-generated content (AIGC) has significantly improved the realism and accessibility of synthetic images. While large image generation models offer immense potential in creative industries, they also introduce serious challenges, including copyright infringement, content authentication, and the traceability of generated images. Digital watermarking has emerged as a promising approach to address these concerns by embedding imperceptible yet detectable signatures into generated images. This survey provides a comprehensive review of three core areas: (1) the evolution of image generation technologies, highlighting key milestones such as the transition from GANs to diffusion models; (2) traditional and state-of-the-art digital image watermarking algorithms, encompassing spatial domain, transform domain, and deep learning-based approaches; (3) watermarking methods specific to AIGC, including ownership authentication of AI model and diffusion model, and watermarking of AI-generated images. Additionally, we examine common performance evaluation metrics used in this field, such as watermark capacity, watermark detection accuracy, fidelity, and robustness. Finally, we discuss the unresolved issues and propose several potential directions for future research. We look forward to this paper offering valuable reference for academics in the field of AIGC watermarking and related fields.

9 July 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
DWDeyang Wu
Deyang Wu
JWJiayan Wang
Jiayan Wang
JZJing Zhao
Jing Zhao
Li LiLi Li
Li Li
Zichi WangZichi Wang
Zichi Wang
HWHanzhou Wu
Hanzhou Wu
An efficient and reliable digital watermarking scheme is needed in a complex network environment to solve image copyright disputes. However, most existing digital watermarking technologies can only resist common image processing and perform poorly against complex attacks. To this end, an adaptive robust watermarking for resisting multiple distortions in real scenes is proposed in this work. First, to reduce the impact of common attacks on the robustness of the algorithm, two-level stationary wavelet transform (SWT) is applied to extract low-frequency sub-band of host image, which is subsequently divided into nonoverlapping sub-blocks. Then, a circular sub-block method is designed for watermark embedding. Moreover, an improved Schur decomposition is proposed to control the variation range of eigenvalues. Meanwhile, an adaptive robust factor and embedding strength strategy are proposed to ensure image reconstruction in real number field, thereby balancing the invisibility and robustness of the watermark. Finally, the logistic encryption and repetition code are performed on the watermark to improve the security and error correction capabilities of the watermark. Extensive experiments demonstrate that the proposed scheme has higher performance than some representative watermarking schemes in complex combined attacks and real-world scenarios.