all AI news
Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
March 15, 2024, 4:41 a.m. | Zhangheng Li, Junyuan Hong, Bo Li, Zhangyang Wang
cs.LG updates on arXiv.org arxiv.org
Abstract: While diffusion models have recently demonstrated remarkable progress in generating realistic images, privacy risks also arise: published models or APIs could generate training images and thus leak privacy-sensitive training information. In this paper, we reveal a new risk, Shake-to-Leak (S2L), that fine-tuning the pre-trained models with manipulated data can amplify the existing privacy risks. We demonstrate that S2L could occur in various standard fine-tuning strategies for diffusion models, including concept-injection methods (DreamBooth and Textual Inversion) …
amplify arxiv cs.lg diffusion diffusion models fine-tuning generative leak privacy risk type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Data Engineer
@ Quantexa | Sydney, New South Wales, Australia
Staff Analytics Engineer
@ Warner Bros. Discovery | NY New York 230 Park Avenue South