Session Chair: Mingyu Gao (Tsinghua Univ.)

MPC-Pipe: an Efficient Pipeline Scheme for Semi-honest MPC Machine Learning
Yongqin Wang (Department of Electrical & Computer Engineering, University of Southern California), Rachit Rajat (Department of Electrical & Computer Engineering, University of Southern California), Murali Annavaram (Department of Electrical & Computer Engineering, University of Southern California)
Paper

Cinnamon: A Framework for Scale-Out Encrypted AI
Siddharth Jayashankar (Carnegie Mellon University), Edward Chen (Carnegie Mellon University), Tom Tang (Carnegie Mellon University), Wenting Zheng (Carnegie Mellon University), Dimitrios Skarlatos (Carnegie Mellon University)
Paper

PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption
Yifan Tan (Institute of Parallel and Distributed Systems, SEIEE, Shanghai Jiao Tong University), Cheng Tan (Northeastern University), Zeyu Mi (Institute of Parallel and Distributed Systems, SEIEE, Shanghai Jiao Tong University), Haibo Chen (Institute of Parallel and Distributed Systems, SEIEE, Shanghai Jiao Tong University)
Paper

Practical Federated Recommendation Model Learning Using ORAM with Controlled Privacy
Jinyu Liu (The Pennsylvania State University), Wenjie Xiong (Virginia Tech), G. Edward Suh (NVIDIA,Cornell University), Kiwan Maeng (The Pennsylvania State University)
Paper

Tackling ML-based Dynamic Mispredictions using Statically Computed Invariants for Attack Surface Reduction
Chris Porter (IBM Research), Sharjeel Khan (Georgia Institute of Technology), Kangqi Ni (Georgia Institute of Technology), Santosh Pande (Georgia Institute of Technology)
Paper