Privacy in Collaborative ML Sep 27, 2018 Differential Privacy Machine Learning Differential Privacy Selected Publications CALIBURN: Self-Calibrated LLM Unlearning Alignment A retention-data-free LLM unlearning method that uses a self-calibrated term to forget targeted knowledge more precisely while preserving general capabilities. Zhengbang Yang, Yisheng Zhong, Junyuan "Jason" Hong, Zhuangdi Zhu PDF Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk We propose a new risk to published generative models that finetuning on generated samples can exacerbate the privacy leakage. Zhangheng Li, Junyuan "Jason" Hong, Bo Li, Zhangyang Wang PDF Code DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer We make local LLMs to engineer privacy-preserving prompts that are transferrable for cloud models. Junyuan "Jason" Hong, Jiachen T. Wang, Chenhui Zhang, Zhangheng Li, Bo Li, Zhangyang Wang PDF Code Understanding Deep Gradient Leakage via Inversion Influence Functions We propose a new metric to efficiently evaluate the privacy risks from gradient inversion and provides new insights. Haobo Zhang, Junyuan "Jason" Hong, Yuyang Deng, Mehrdad Mahdavi, Jiayu Zhou PDF Code Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling We propose a new privacy-preserving learning framework, outsourcing training to cloud without uploading data, which provides more data without injecting noise into gradient or samples. Junyuan "Jason" Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger PDF Poster Slides Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent Protecting privacy in learning while maintaining the model performance has become increasingly critical in many applications that … Junyuan "Jason" Hong, Zhangyang Wang, Jiayu Zhou Preprint Slides Learning Model-Based Privacy Protection under Budget Constraints Protecting privacy in gradient-based learning has become increasingly critical as more sensitive information is being used. Many … Junyuan "Jason" Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou PDF Slides Video Supplementary
Differential Privacy
Differential Privacy
Differential Privacy
Differential Privacy
