5 papers
OpenPCC: Open and Confidential LLM Serving on Commodity TEEs
Haoling Zhou, Shixuan Zhao, Chao Wang +1
Generative AI applications such as personal AI agents, image generators, and chat assistants offer advanced capabilities to improve user experience. Behind the scenes, Large Langua…
Too Private to Tell: Practical Token Theft Attacks on Apple Intelligence
Haoling Zhou, Shixuan Zhao, Chao Wang +1
Apple Intelligence is a generative AI (GenAI) service provided by Apple on its devices. While offering a similar set of features as other similar GenAI services, Apple Intelligence…
Blueprint, Bootstrap, and Bridge: A Security Look at NVIDIA GPU Confidential Computing
Zhongshu Gu, Enriquillo Valdez, Salman Ahmed +5
NVIDIA GPU Confidential Computing (GPU-CC) aims to provide secure execution for AI workloads. For end users, enabling GPU-CC is seamless and requires no modifications to existing a…
Styx: Collaborative and Private Data Processing With TEE-Enforced Sticky Policy
Shixuan Zhao, Weicheng Wang, Ninghui Li +1
Protecting sensitive information in data-driven collaborations, such as AI training, while meeting the diverse requirements of multiple mutually distrusted stakeholders, is both cr…
Ditto: Elastic Confidential VMs with Secure and Dynamic CPU Scaling
Shixuan Zhao, Mengyuan Li, Mengjia Yan +1
Confidential Virtual Machines (CVMs) are a type of VMbased Trusted Execution Environments (TEEs) designed to enhance the security of cloud-based VMs, safeguarding them even from ma…