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 nonsecure 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.
Blind signatures are well-studied building blocks of cryptography, originally designed to enable anonymity in electronic voting and digital banking. Identity-based signature were introduced by Shamir in 1984 and gave an alternative to prominent Public Key Infrastructure. An identity-based blind signature (IDBS) allows any user to interact directly with the signer without any prior interaction with a trusted authority. The first IDBS has been proposed in 2002 and several schemes were proposed since then. Seeking for a full comparison of these primitives, we propose a survey on IDBS and list all such primitives that seems to maintain some security. We also classify their security assumptions based on the existing security expectation that have not been formalized yet in the literature. Moreover, we empirically evaluate the complexity of all the operations used in those schemes with modern cryptographic libraries. This allows us to perform a realistic evaluation of their practical complexities. Hence, we can compare all schemes in terms of complexity and signature size.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.