Showing 2026Show all
3 papers · 1 filter
cs.CR2026
When Do Differentially Private Inputs Protect Graph Shift Operators?
Andrew Campbell, Chenyue Zhang, Hang Liu +3
We study the differential privacy (DP) of a graph shift operator (GSO) when an analyst observes the output of a graph filter. In particular, we study the setting in which the input…
cs.IT2026
Reconstruction Limits for Repeated Differentially Private Aggregates: A Cramer-Rao Perspective on Query Geometry
Chenyue Zhang, Andrew Campbell, Anna Scaglione +1
Repeated differentially private (DP) releases are often evaluated by transcript length or cumulative privacy accounting. We show that these quantities do not by themselves determin…
eess.SP2026
Enabling Safety-Critical Wireless Communications via Safe Reinforcement Learning
Haoran Peng, Tong Wu, Hang Liu +3
Ensuring strict safety guarantees is the paramount challenge for emerging 5G/6G wireless systems, particularly as they increasingly govern mission-critical applications ranging fro…