activity
20242026
collaborators

8 papers

cs.CR2026

OTRO: Oblivious Tokenization Path with Square-Root ORAM

Jonghyun Lee, Yongqin Wang, Rachit Rajat +3

The CPU-side large language model (LLM) tokenizer is a critical security gap in LLM serving through a confidential computing stack with CPU and GPU trusted execution environments (…

cs.AI2026

MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents

Haonan Li, Tianjun Sun, Yongqing Wang +1

Multi-server MCP agents create an information-flow control problem: faithful tool composition can turn individually benign read/write permissions into cross-boundary credential pro…

cs.CR2026

LRD-MPC: Efficient MPC Inference through Low-rank Decomposition

Tingting Tang, Yongqin Wang, Murali Annavaram

Secure Multi-party Computation (MPC) enables untrusted parties to jointly compute a function without revealing their inputs. Its application to machine learning (ML) has gained sig…

cs.CR2026

Differentially Private Retrieval-Augmented Generation

Tingting Tang, James Flemings, Yongqin Wang +1

Retrieval-augmented generation (RAG) is a widely used framework for reducing hallucinations in large language models (LLMs) on domain-specific tasks by retrieving relevant document…

cs.CR2025

Characterization of GPU TEE Overheads in Distributed Data Parallel ML Training

Jonghyun Lee, Yongqin Wang, Rachit Rajat +1

Confidential computing (CC) or trusted execution enclaves (TEEs) is now the most common approach to enable secure computing in the cloud. The recent introduction of GPU TEEs by NVI…

cs.CR2025

High-Throughput Secure Multiparty Computation with an Honest Majority in Various Network Settings

Christopher Harth-Kitzerow, Ajith Suresh, Yongqin Wang +3

In this work, we present novel protocols over rings for semi-honest secure three-party computation (3PC) and malicious four-party computation (4PC) with one corruption. While most…