HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

SAMBA: A Generic Framework for Secure Federated Multi-Armed Bandits

Abstract : The multi-armed bandit is a reinforcement learning model where a learning agent repeatedly chooses an action (pull a bandit arm) and the environment responds with a stochastic outcome (reward) coming from an unknown distribution associated with the chosen arm. Bandits have a wide-range of application such as Web recommendation systems. We address the cumulative reward maximization problem in a secure federated learning setting, where multiple data owners keep their data stored locally and collaborate under the coordination of a central orchestration server. We rely on cryptographic schemes and propose SAMBA, a generic framework for Secure federAted Multi-armed BAndits. Each data owner has data associated to a bandit arm and the bandit algorithm has to sequentially select which data owner is solicited at each time step. We instantiate SAMBA for five bandit algorithms. We show that SAMBA returns the same cumulative reward as the non-secure versions of bandit algorithms, while satisfying formally proven security properties. We also show that the overhead due to cryptographic primitives is linear in the size of the input, which is confirmed by our proof-of-concept implementation. https://www.jair.org/index.php/jair/article/view/13163
Complete list of metadata

Contributor : Radu Ciucanu Connect in order to contact the contributor
Submitted on : Thursday, February 3, 2022 - 9:22:47 AM
Last modification on : Thursday, March 3, 2022 - 7:00:03 PM


  • HAL Id : hal-03553894, version 1


Radu Ciucanu, Pascal Lafourcade, Gael Marcadet, Marta Soare. SAMBA: A Generic Framework for Secure Federated Multi-Armed Bandits. Journal of Artificial Intelligence Research, Association for the Advancement of Artificial Intelligence, 2022, 73, pp.737--765. ⟨hal-03553894⟩



Record views