5 papers
Private Retrieval Augmented Generation via Random Projection
Dixi Yao, Tahseen Rabbani, Tian Li
Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by querying external structured knowledge. However, it can also introduce privacy ris…
Persistent Watermarking of Text-to-Image Models
Dixi Yao, Kaiwen Chen, Tahseen Rabbani +1
Text-to-image (T2I) generation is gaining increasing popularity with the general public, motivating the development of reliable mechanisms for copyrighting such models given their…
Asynchronous Heavy-Tailed Optimization
Junfei Sun, Dixi Yao, Xuchen Gong +3
Heavy-tailed stochastic gradient noise, commonly observed in transformer models, can destabilize the optimization process. Recent works mainly focus on developing and understanding…
Enhancing Privacy in ControlNet and Stable Diffusion via Split Learning
Dixi Yao
With the emerging trend of large generative models, ControlNet is introduced to enable users to fine-tune pre-trained models with their own data for various use cases. A natural qu…
Risks When Sharing LoRA Fine-Tuned Diffusion Model Weights
Dixi Yao
With the emerging trend in generative models and convenient public access to diffusion models pre-trained on large datasets, users can fine-tune these models to generate images of…