Secure protocols for cumulative reward maximization in stochastic multi-armed bandits - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Journal of Computer Security Année : 2022

Secure protocols for cumulative reward maximization in stochastic multi-armed bandits

Résumé

We consider the problem of cumulative reward maximization in multi-armed bandits. We address the security concerns that occur when data and computations are outsourced to an honest-but-curious cloud i.e., that executes tasks dutifully, but tries to gain as much information as possible. We consider situations where data used in bandit algorithms is sensitive and has to be protected e.g., commercial or personal data. We rely on cryptographic schemes and propose UCB - MS, a secure multi-party protocol based on the UCB algorithm. We prove that UCB - MS computes the same cumulative reward as UCB while satisfying desirable security properties. In particular, cloud nodes cannot learn the cumulative reward or the sum of rewards for more than one arm. Moreover, by analyzing messages exchanged among cloud nodes, an external observer cannot learn the cumulative reward or the sum of rewards produced by some arm. We show that the overhead due to cryptographic primitives is linear in the size of the input. Our implementation confirms the linear-time behavior and the practical feasibility of our protocol, on both synthetic and real-world data.
Fichier non déposé

Dates et versions

hal-03564146 , version 1 (10-02-2022)

Identifiants

Citer

Radu Ciucanu, Pascal Lafourcade, Marius Lombard-Platet, Marta Soare. Secure protocols for cumulative reward maximization in stochastic multi-armed bandits. Journal of Computer Security, 2022, pp.1-27. ⟨10.3233/JCS-210051⟩. ⟨hal-03564146⟩
108 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More