Cheng Hong
Research Subjects
Cheng Hong has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Zhicong Huang
Ant Group, Hangzhou, China
3 shared publications - Chao Niu
Ant Group
2 shared publications - Axin Wu
State Key Laboratory of Cryptology
1 shared publication - Benqiang Wei
Ant Group, Singapore, Singapore
1 shared publication - Chi Zhang
Shanghai Jiao Tong University
1 shared publication - Dawu Gu
Shanghai Jiao Tong University
1 shared publication
Latest Publications
- 4 November 2026
- Published by Springer Nature
- p. 364-384
Parallel Block-Cipher-Based AEAD Mode for MPC Transciphering
- 4 November 2026
- Published by Springer Nature
- p. 364-384
Parallel Block-Cipher-Based AEAD Mode for MPC Transciphering
- 12 October 2025
- Published by Springer Nature
- p. 63-85
Privacy-Preserving k-Nearest Neighbor Query: Faster and More Secure
- 12 October 2025
- Published by Springer Nature
- p. 63-85
Privacy-Preserving k-Nearest Neighbor Query: Faster and More Secure
- Open Access
- 5 June 2025
- Published by Universitatsbibliothek der Ruhr-Universitat Bochum in IACR Transactions on Cryptographic Hardware and Embedded Systems
- Vol. 2025 (3) , 583-613
SoK: FHE-Friendly Symmetric Ciphers and Transciphering
Fully Homomorphic Encryption (FHE) enables computation on encrypted data without decryption, demonstrating significant potential for privacy-preserving applications. However, FHE faces several challenges, one of which is the significant plaintext-to-ciphertext expansion ratio, resulting in high communication overhead between client and server. The transciphering technique can effectively address this problem by first encrypting data with a space-efficient symmetric cipher, then converting symmetric ciphertext to FHE ciphertext without decryption.Numerous FHE-friendly symmetric ciphers and transciphering methods have been developed by researchers, each with unique advantages and limitations. These often require extensive knowledge of both symmetric cryptography and FHE to fully grasp, making comparison and selection among these schemes challenging. To address this, we conduct a comprehensive survey of over 20 FHE-friendly symmetric ciphers and transciphering methods, evaluating them based on criteria such as security level, efficiency, and compatibility. We have designed and executed experiments to benchmark the performance of the feasible combinations of symmetric ciphers and transciphering methods across various application scenarios. Our findings offer insights into achieving efficient transciphering tailored to different task contexts. Additionally, we make our example code available open-source, leveraging state-of-the-art FHE implementations.
- 5 June 2025
- Published by Universitatsbibliothek der Ruhr-Universitat Bochum in IACR Transactions on Cryptographic Hardware and Embedded Systems
- Vol. 2025 (3) , 583-613
Open AccessSoK: FHE-Friendly Symmetric Ciphers and Transciphering
Fully Homomorphic Encryption (FHE) enables computation on encrypted data without decryption, demonstrating significant potential for privacy-preserving applications. However, FHE faces several challenges, one of which is the significant plaintext-to-ciphertext expansion ratio, resulting in high communication overhead between client and server. The transciphering technique can effectively address this problem by first encrypting data with a space-efficient symmetric cipher, then converting symmetric ciphertext to FHE ciphertext without decryption.Numerous FHE-friendly symmetric ciphers and transciphering methods have been developed by researchers, each with unique advantages and limitations. These often require extensive knowledge of both symmetric cryptography and FHE to fully grasp, making comparison and selection among these schemes challenging. To address this, we conduct a comprehensive survey of over 20 FHE-friendly symmetric ciphers and transciphering methods, evaluating them based on criteria such as security level, efficiency, and compatibility. We have designed and executed experiments to benchmark the performance of the feasible combinations of symmetric ciphers and transciphering methods across various application scenarios. Our findings offer insights into achieving efficient transciphering tailored to different task contexts. Additionally, we make our example code available open-source, leveraging state-of-the-art FHE implementations.
- Open Access
VideoMarkBench: Benchmarking Robustness of Video Watermarking
The rapid development of video generative models has led to a surge in highly realistic synthetic videos, raising ethical concerns related to disinformation and copyright infringement. Recently, video watermarking has been proposed as a mitigation strategy by embedding invisible marks into AI-generated videos to enable subsequent detection. However, the robustness of existing video watermarking methods against both common and adversarial perturbations remains underexplored. In this work, we introduce VideoMarkBench, the first systematic benchmark designed to evaluate the robustness of video watermarks under watermark removal and watermark forgery attacks. Our study encompasses a unified dataset generated by three state-of-the-art video generative models, across three video styles, incorporating four watermarking methods and seven aggregation strategies used during detection. We comprehensively evaluate 12 types of perturbations under white-box, black-box, and no-box threat models. Our findings reveal significant vulnerabilities in current watermarking approaches and highlight the urgent need for more robust solutions. Our code is available at https://github.com/zhengyuan-jiang/VideoMarkBench.
Open AccessVideoMarkBench: Benchmarking Robustness of Video Watermarking
The rapid development of video generative models has led to a surge in highly realistic synthetic videos, raising ethical concerns related to disinformation and copyright infringement. Recently, video watermarking has been proposed as a mitigation strategy by embedding invisible marks into AI-generated videos to enable subsequent detection. However, the robustness of existing video watermarking methods against both common and adversarial perturbations remains underexplored. In this work, we introduce VideoMarkBench, the first systematic benchmark designed to evaluate the robustness of video watermarks under watermark removal and watermark forgery attacks. Our study encompasses a unified dataset generated by three state-of-the-art video generative models, across three video styles, incorporating four watermarking methods and seven aggregation strategies used during detection. We comprehensively evaluate 12 types of perturbations under white-box, black-box, and no-box threat models. Our findings reveal significant vulnerabilities in current watermarking approaches and highlight the urgent need for more robust solutions. Our code is available at https://github.com/zhengyuan-jiang/VideoMarkBench.
- Open Access
- 18 October 2024
- Published by EDP Sciences in Security and Safety
- Vol. 4
Recent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption
Fully Homomorphic Encryption (FHE), known for its ability to process encrypted data without decryption, is a promising technique for solving privacy concerns in the machine learning era. However, there are many kinds of available FHE schemes and way more FHE-based solutions in the literature, and they are still fast evolving, making it difficult to get a complete view. This article aims to introduce recent representative results of FHE-based privacy-preserving machine learning, helping users understand the pros and cons of different kinds of solutions, and choose an appropriate approach for their needs.
- 18 October 2024
- Published by EDP Sciences in Security and Safety
- Vol. 4
Open AccessRecent advances of privacy-preserving machine learning based on (Fully) Homomorphic Encryption
Fully Homomorphic Encryption (FHE), known for its ability to process encrypted data without decryption, is a promising technique for solving privacy concerns in the machine learning era. However, there are many kinds of available FHE schemes and way more FHE-based solutions in the literature, and they are still fast evolving, making it difficult to get a complete view. This article aims to introduce recent representative results of FHE-based privacy-preserving machine learning, helping users understand the pros and cons of different kinds of solutions, and choose an appropriate approach for their needs.
- Open Access
PUMA: Secure Inference of LLaMA-7B in Five Minutes
With ChatGPT as a representative, tons of companies have began to provide services based on large Transformers models. However, using such a service inevitably leak users' prompts to the model provider. Previous studies have studied secure inference for Transformer models using secure multiparty computation (MPC), where model parameters and clients' prompts are kept secret. Despite this, these frameworks are still limited in terms of model performance, efficiency, and deployment. To address these limitations, we propose framework PUMA to enable fast and secure Transformer model inference. Our framework designs high quality approximations for expensive functions such as GeLU and softmax, and significantly reduce the cost of secure inference while preserving the model performance. Additionally, we design secure Embedding and LayerNorm procedures that faithfully implement the desired functionality without undermining the Transformer architecture. PUMA is about $2\times$ faster than the state-of-the-art framework MPCFORMER(ICLR 2023) and has similar accuracy as plaintext models without fine-tuning (which the previous works failed to achieve). PUMA can even evaluate LLaMA-7B in around 5 minutes to generate 1 token. To our best knowledge, this is the first time that a model with such a parameter size is able to be evaluated under MPC. PUMA has been open-sourced in the Github repository of SecretFlow-SPU.Open AccessPUMA: Secure Inference of LLaMA-7B in Five Minutes
With ChatGPT as a representative, tons of companies have began to provide services based on large Transformers models. However, using such a service inevitably leak users' prompts to the model provider. Previous studies have studied secure inference for Transformer models using secure multiparty computation (MPC), where model parameters and clients' prompts are kept secret. Despite this, these frameworks are still limited in terms of model performance, efficiency, and deployment. To address these limitations, we propose framework PUMA to enable fast and secure Transformer model inference. Our framework designs high quality approximations for expensive functions such as GeLU and softmax, and significantly reduce the cost of secure inference while preserving the model performance. Additionally, we design secure Embedding and LayerNorm procedures that faithfully implement the desired functionality without undermining the Transformer architecture. PUMA is about $2\times$ faster than the state-of-the-art framework MPCFORMER(ICLR 2023) and has similar accuracy as plaintext models without fine-tuning (which the previous works failed to achieve). PUMA can even evaluate LLaMA-7B in around 5 minutes to generate 1 token. To our best knowledge, this is the first time that a model with such a parameter size is able to be evaluated under MPC. PUMA has been open-sourced in the Github repository of SecretFlow-SPU.