PrismDM: An Accurate and Efficient Framework for Privacy-Preserving Diffusion Model Sampling
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 15079-15088
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62372362)
- National Natural Science Foundation of China (62502372)
- National Natural Science Foundation of China (62272372)
- National Natural Science Foundation of China (62272379)
- Xi'an Jiaotong University–China Mobile Communications Group Co., Ltd. Joint Institute (None)
This publication has 25 references indexed in Scilit:
- Accurate structure prediction of biomolecular interactions with AlphaFold 3Nature, 2024
- Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk2024
- A survey on large language model (LLM) security and privacy: The Good, The Bad, and The UglyHigh-Confidence Computing, 2024
- Diffusion models in bioinformatics and computational biologyNature Reviews Bioengineering, 2023
- Imagic: Text-Based Real Image Editing with Diffusion Models2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Privacy-Preserving Machine Learning: Threats and SolutionsIEEE Security & Privacy, 2019
- Microsoft COCO: Common Objects in Context2014
- Security and Composition of Multiparty Cryptographic ProtocolsJournal of Cryptology, 2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998