Publications (27)
Secure Federated XGBoost with CUDA-accelerated Homomorphic Encryption via NVIDIA FLARE
Ziyue Xu, Yuan-Ting Hsieh, Zhihong Zhang +4
Federated learning (FL) enables collaborative model training across decentralized datasets. NVIDIA FLARE's Federated XGBoost extends the popular XGBoost algorithm to both vertical…
Empowering Federated Learning for Massive Models with NVIDIA FLARE
Holger R. Roth, Ziyue Xu, Yuan-Ting Hsieh +12
In the ever-evolving landscape of artificial intelligence (AI) and large language models (LLMs), handling and leveraging data effectively has become a critical challenge. Most stat…
DART: Depth-Enhanced Accurate and Real-Time Background Matting
Hanxi Li, Guofeng Li, Bo Li +2
Matting with a static background, often referred to as ``Background Matting" (BGM), has garnered significant attention within the computer vision community due to its pivotal role…
C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System
Parker Addison, Minh-Tuan H. Nguyen, Tomislav Medan +13
Organizations seeking to utilize Large Language Models (LLMs) for knowledge querying and analysis often encounter challenges in maintaining an LLM fine-tuned on targeted, up-to-dat…
Phase transitions in typical fluorite-type ferroelectrics
Heng Yu, Kan-Hao Xue, Nan Feng +4
While ferroelectric hafnia () has become a technically important material for microelectronics, the physical origin of its ferroelectricity remains poorly understoo…
Chosen-Plaintext Attacks of Double Random Phase Encryption with Nonlinear Optical Media
Yan Cheng, Yiwei Chen, Kui Ren +1
This paper studies an inverse problem in nonlinear optical encryption. We examine chosen-plaintext attacks (CPA) on a nonlinear optical encryption strategy that integrates double r…