Preprint
Sep 2026
Lower Bounds for Private Graph Optimization Problems using Reconstruction Attacks
This paper studies fundamental graph optimization problems under differential privacy (DP) and shows new, reconstruction-based lower bounds for large families of sparse graphs with expansion properties and extends lower bounds of Deng et al. (ICLR~'25) to general graphs and to approximate DP.
Jacob Imola, Rasmus Pagh, Lukas Retschmeier
· 1 citation