2 papers
cs.CR2026
From Review to Authorization: Key-Isolated Threshold Signing for LLM Agents
Yu Zheng, Qizhi Zhang
Autonomous LLM agents can turn semantic judgments into consequential actions such as payments and permission changes. If the same process makes these judgments and controls a reusa…
cs.CR2025
VIRGOS: Secure Graph Convolutional Network on Vertically Split Data from Sparse Matrix Decomposition
Yu Zheng, Qizhi Zhang, Lichun Li +2
Securely computing graph convolutional networks (GCNs) is critical for applying their analytical capabilities to privacy-sensitive data like social/credit networks. Multiplying a s…