Locally Private and Robust Multi-Armed Bandits

We study the interplay between local differential privacy (LDP) and robustness to Huber corruption and possibly heavy-tailed rewards in the context of multi-armed bandits (MABs). We consider two different practical settings: LDP-then-Corruption (L TC) where each user's locally private response might be further corrupted during the data collection process, and Corruption-then-LDP (CTL)