2 papers
cs.LG2026
MaxModShift: Model Privacy via Designed Shifts
Nomaan A. Kherani, Urbashi Mitra
Model learning by an eavesdropper is treated as an estimation problem in a federated environment. The Fisher Information Matrix for the eavesdropper's estimation problem is driven…
cs.LG2025
ModShift: Model Privacy via Designed Shifts
Nomaan A. Kherani, Urbashi Mitra
In this paper, shifts are introduced to preserve model privacy against an eavesdropper in federated learning. Model learning is treated as a parameter estimation problem. This pers…