Zihan Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zihan Yuan has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Zichi Wang
School of Communication and Information Engineering, Shanghai University, Shanghai, China
6 shared publications - Xinpeng Zhang
Fudan University, Shanghai, China
5 shared publications - Li Li
School of Communication and Information Engineering, Shanghai University, Shanghai, China
4 shared publications Xinpeng Zhang
3 shared publications- Guanghui He
School of Communication and Information Engineering, Shanghai University, Shanghai, China
2 shared publications - Jingyuan Jiang
School of Communication and Information Engineering, Shanghai University, Shanghai, China
2 shared publications
Latest Publications
- 15 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (14) , 32467
Erratum to “Verifiable Privacy-Preserving Neural Network Inference via Multi-Key Homomorphic Encryption”
- 15 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (14) , 32467
Erratum to “Verifiable Privacy-Preserving Neural Network Inference via Multi-Key Homomorphic Encryption”
- 25 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 22072-22081
Verifiable Privacy-Preserving Neural Network Inference via Multi-Key Homomorphic Encryption
With the proliferation of Internet of Things (IoT) devices, deep learning model inference that guarantees data privacy has attracted significant research interest. Secure inference based on homomorphic encryption offers a promising solution by ensuring rigorous data confidentiality. However, in typical cloud-based inference services, ciphertexts are encrypted under a single key, requiring all participants to share the same decryption key. This contradicts real-world scenarios, where multiple participants (e.g., individual IoT devices or users) typically hold their own private keys. To address this issue, this article designs a series of secure sub-protocols based on multi-key homomorphic encryption (MK-HE), enabling the computation of nonlinear functions while preserving data privacy across multiple keys. Furthermore, considering the potentially malicious nature of cloud servers, we incorporate a commitment protocol to ensure the verifiability of inference results and prevent the server from returning incorrect outcomes. Theoretical and security analyses demonstrate the efficiency and privacy of our proposed protocol, which achieves lower computational time and reduced communication overhead without compromising security.
- 25 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 22072-22081
Verifiable Privacy-Preserving Neural Network Inference via Multi-Key Homomorphic Encryption
With the proliferation of Internet of Things (IoT) devices, deep learning model inference that guarantees data privacy has attracted significant research interest. Secure inference based on homomorphic encryption offers a promising solution by ensuring rigorous data confidentiality. However, in typical cloud-based inference services, ciphertexts are encrypted under a single key, requiring all participants to share the same decryption key. This contradicts real-world scenarios, where multiple participants (e.g., individual IoT devices or users) typically hold their own private keys. To address this issue, this article designs a series of secure sub-protocols based on multi-key homomorphic encryption (MK-HE), enabling the computation of nonlinear functions while preserving data privacy across multiple keys. Furthermore, considering the potentially malicious nature of cloud servers, we incorporate a commitment protocol to ensure the verifiability of inference results and prevent the server from returning incorrect outcomes. Theoretical and security analyses demonstrate the efficiency and privacy of our proposed protocol, which achieves lower computational time and reduced communication overhead without compromising security.
- Open Access
- 21 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (12) , 1-21
Integrity Protection of Generative Adversarial Networks Using Fragile Watermarking
Deep learning has made remarkable achievements in the field of artificial intelligence. However, a well-trained deep neural network is at risk of being tampered with. Although some model watermarking schemes have been proposed to solve this problem, most of them are only oriented to discriminant models, and the integrity authentication schemes for generative models are urgently lacking. Especially, the integrity authentication problem of generative adversarial networks (GANs) that plays an important role in computer vision has not been properly solved. To address this problem, we propose a fragile model watermarking framework for GANs. Specifically, we use a secret key to generate specific information as the label and combine it with the watermark to form a trigger set. Then, we use the trigger set to train the GAN, the training process does not damage the model performance. We can achieve integrity authentication of the GAN using the output of the GAN for the specific label. A large number of experiments show that our proposed method has excellent performance, which can realize the integrity authentication of GANs. What’s more, the proposed method has good generalization and can be easily applied to different GAN architectures.
- 21 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (12) , 1-21
Open AccessIntegrity Protection of Generative Adversarial Networks Using Fragile Watermarking
Deep learning has made remarkable achievements in the field of artificial intelligence. However, a well-trained deep neural network is at risk of being tampered with. Although some model watermarking schemes have been proposed to solve this problem, most of them are only oriented to discriminant models, and the integrity authentication schemes for generative models are urgently lacking. Especially, the integrity authentication problem of generative adversarial networks (GANs) that plays an important role in computer vision has not been properly solved. To address this problem, we propose a fragile model watermarking framework for GANs. Specifically, we use a secret key to generate specific information as the label and combine it with the watermark to form a trigger set. Then, we use the trigger set to train the GAN, the training process does not damage the model performance. We can achieve integrity authentication of the GAN using the output of the GAN for the specific label. A large number of experiments show that our proposed method has excellent performance, which can realize the integrity authentication of GANs. What’s more, the proposed method has good generalization and can be easily applied to different GAN architectures.
- 1 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (9) , 8907-8916
Generative Image Steganography Based on Text-to-Image Multimodal Generative Model
Image steganography, the technique of hiding secret messages within images, has recently advanced with generative image steganography, which hides messages during image creation. However, current generative steganography methods often face criticism for their low extraction accuracy and poor robustness—particularly their vulnerability to JPEG compression. To address these challenges, we propose a novel generative image steganography method based on the text-to-image multimodal generative model (StegaMGM). StegaMGM utilizes the initial random normalization distribution in the generative process of latent diffusion models (LDMs), the secret message is hidden in the generated image through message sampling, ensuring it follows the same probability distribution as typical image generative. The content of the stego image can also be controlled through the prompts. On the receiver side, using the shared prompt and diffusion inversion, can extract secret message with high accuracy. In the experimental section, we conducted detailed experiments to demonstrate the advantages of our proposed StegaMGM framework in extraction accuracy, resistance to JPEG compression, and security.
- 1 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (9) , 8907-8916
Generative Image Steganography Based on Text-to-Image Multimodal Generative Model
Image steganography, the technique of hiding secret messages within images, has recently advanced with generative image steganography, which hides messages during image creation. However, current generative steganography methods often face criticism for their low extraction accuracy and poor robustness—particularly their vulnerability to JPEG compression. To address these challenges, we propose a novel generative image steganography method based on the text-to-image multimodal generative model (StegaMGM). StegaMGM utilizes the initial random normalization distribution in the generative process of latent diffusion models (LDMs), the secret message is hidden in the generated image through message sampling, ensuring it follows the same probability distribution as typical image generative. The content of the stego image can also be controlled through the prompts. On the receiver side, using the shared prompt and diffusion inversion, can extract secret message with high accuracy. In the experimental section, we conducted detailed experiments to demonstrate the advantages of our proposed StegaMGM framework in extraction accuracy, resistance to JPEG compression, and security.
- 26 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 1470-1474
Watermark Removal Attack Against Text-to-Image Generative Model Watermarking
The artist's style can be quickly imitated by fine-tuning a text-to-image model using artist's artworks, which raises serious copyright concerns. Scholars have proposed many watermarking methods to protect the artists' copyright. To evaluate the security and enhance the performance of existing watermarking, this paper proposes a watermark removal attack for text-to-image generative model watermarking for the first time. This attack aims to invalidate watermarking designed to detect art theft mimicry in text-to-image models. In this method, a watermark recognition network and a watermark removal network are designed. The watermark recognition network identifies whether an artwork contains watermark, and the watermark removal network is used to remove it. Consequently, text-to-image models fine-tuned with watermark-removed artworks can reproduce an artist's style while evading watermark detection. This makes the copyright authentication of artworks ineffective. Experiments show that the proposed attack can effectively remove watermarks, with watermark extraction accuracy dropping below 48.64%. Additionally, the images after watermark removal retain high similarity to the original images, with PSNR exceeding 27.96 and SSIM exceeding 0.92.
- 26 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 1470-1474
Watermark Removal Attack Against Text-to-Image Generative Model Watermarking
The artist's style can be quickly imitated by fine-tuning a text-to-image model using artist's artworks, which raises serious copyright concerns. Scholars have proposed many watermarking methods to protect the artists' copyright. To evaluate the security and enhance the performance of existing watermarking, this paper proposes a watermark removal attack for text-to-image generative model watermarking for the first time. This attack aims to invalidate watermarking designed to detect art theft mimicry in text-to-image models. In this method, a watermark recognition network and a watermark removal network are designed. The watermark recognition network identifies whether an artwork contains watermark, and the watermark removal network is used to remove it. Consequently, text-to-image models fine-tuned with watermark-removed artworks can reproduce an artist's style while evading watermark detection. This makes the copyright authentication of artworks ineffective. Experiments show that the proposed attack can effectively remove watermarks, with watermark extraction accuracy dropping below 48.64%. Additionally, the images after watermark removal retain high similarity to the original images, with PSNR exceeding 27.96 and SSIM exceeding 0.92.
- 28 September 2024
- Published by Elsevier in Signal Processing
- Vol. 227
Protecting copyright of stable diffusion models from ambiguity attacks
- 28 September 2024
- Published by Elsevier in Signal Processing
- Vol. 227
Protecting copyright of stable diffusion models from ambiguity attacks
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (21) , 35238-35249
Watermarking for Stable Diffusion Models
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.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (21) , 35238-35249
Watermarking for Stable Diffusion Models
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.
- 10 April 2024
- Published by Elsevier in Signal Processing
- Vol. 221
Ambiguity attack against text-to-image diffusion model watermarking
- 10 April 2024
- Published by Elsevier in Signal Processing
- Vol. 221
Ambiguity attack against text-to-image diffusion model watermarking
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 8 (4) , 2775-2790
Semi-Fragile Neural Network Watermarking Based on Adversarial Examples
Deep neural networks (DNNs) may be subject to various modifications during transmission and use. Regular processing operations do not affect the functionality of a model, while malicious tampering will cause serious damage. Therefore, it is crucial to determine the availability of a DNN model. To address this issue, we propose a semi-fragile black-box watermarking method that can distinguish between accidental modification and malicious tampering of DNNs, focusing on the privacy and security of neural network models. Specifically, for a given model, a strategy is designed to generate semi-fragile and sensitive samples using adversarial example techniques without decreasing the model accuracy. The model outputs for these samples are extremely sensitive to malicious tampering and robust to accidental modification. According to these properties, accidental modification and malicious tampering can be distinguished to assess the availability of a watermarked model. Extensive experiments demonstrate that the proposed method can detect malicious model tampering with high accuracy up to 100% while tolerating accidental modifications such as fine-tuning, pruning, and quantitation with the accuracy exceed 75%. Moreover, our semi-fragile neural network watermarking approach can be easily extended to various DNNs.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 8 (4) , 2775-2790
Semi-Fragile Neural Network Watermarking Based on Adversarial Examples
Deep neural networks (DNNs) may be subject to various modifications during transmission and use. Regular processing operations do not affect the functionality of a model, while malicious tampering will cause serious damage. Therefore, it is crucial to determine the availability of a DNN model. To address this issue, we propose a semi-fragile black-box watermarking method that can distinguish between accidental modification and malicious tampering of DNNs, focusing on the privacy and security of neural network models. Specifically, for a given model, a strategy is designed to generate semi-fragile and sensitive samples using adversarial example techniques without decreasing the model accuracy. The model outputs for these samples are extremely sensitive to malicious tampering and robust to accidental modification. According to these properties, accidental modification and malicious tampering can be distinguished to assess the availability of a watermarked model. Extensive experiments demonstrate that the proposed method can detect malicious model tampering with high accuracy up to 100% while tolerating accidental modifications such as fine-tuning, pruning, and quantitation with the accuracy exceed 75%. Moreover, our semi-fragile neural network watermarking approach can be easily extended to various DNNs.
- 26 August 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 236
Semi-fragile neural network watermarking for content authentication and tampering localization
- 26 August 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 236
Semi-fragile neural network watermarking for content authentication and tampering localization