{"type":"ScholarlyArticle","title":"SAMBA: A Generic Framework for Secure Federated Multi-Armed Bandits (Extended Abstract)","authors":[{"name":"Radu Ciucanu","slug":"radu-ciucanu","given":"Radu","family":"Ciucanu","affiliation":"INSA Centre Val de Loire , LIFO EA 4022 , France"},{"name":"Pascal Lafourcade","slug":"pascal-lafourcade","given":"Pascal","family":"Lafourcade","affiliation":"Université Clermont Auvergne , LIMOS UMR 6158 , France"},{"name":"Gael Marcadet","slug":"gael-marcadet","given":"Gael","family":"Marcadet","affiliation":"Université Clermont Auvergne , LIMOS UMR 6158 , France"},{"name":"Marta Soare","slug":"marta-soare","given":"Marta","family":"Soare","affiliation":"Université d'Orléans , Université Grenoble Alpes , LIG UMR 5217 , France"}],"abstract":"We tackle the problem of secure cumulative reward maximization in multi-armed bandits in a cross-silo federated learning setting. Under the orchestration of a central server, each data owner participating at the cumulative reward computation has the guarantee that its raw data is not seen by some other participant. We rely on cryptographic schemes and propose SAMBA, a generic framework for Secure federAted Multi-armed BAndits. 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 implementation.","doi":"10.24963/ijcai.2023/772","url":"https://ijcai.org/proceedings/2023/772","pdf":"https://ijcai.org/proceedings/2023/0772.pdf","markdown":"https://ijcai.org/proceedings/2023/772.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/772","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Journal Track","track":"Journal Track","number":772,"pages":{"first":6863,"last":6867},"keywords":["Multidisciplinary Topics and Applications: MDA: Security and privacy","Machine Learning: ML: Federated learning","Uncertainty in AI: UAI: Sequential decision making"],"videos":[],"references":[{"position":1,"raw":"[Cheon et al., 2020] J. H. Cheon, D. Kim, and D. Kim. Ef- ficient Homomorphic Comparison Methods with Optimal Complexity. In ASIACRYPT, pages 221-256, 2020.","title":"Efficient Homomorphic Comparison Methods with Optimal Complexity","authors":"J H Cheon, D Kim, D Kim","year":"2020","venue":"ASIACRYPT","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ciucanu et al., 2019] R. Ciucanu, P. Lafourcade, M. Lombard-Platet, and M. Soare. Secure Best Arm Identification in Multi-Armed Bandits. In Interna- tional Conference on Information Security Practice and Experience (ISPEC), pages 152-171, 2019.","title":"Secure Best Arm Identification in Multi-Armed Bandits","authors":"R Ciucanu, P Lafourcade, M Lombard-Platet, M Soare","year":"2019","venue":"International Conference on Information Security Practice and Experience (ISPEC)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ciucanu et al., 2020a] R. Ciucanu, A. Delabrouille, P. Lafourcade, and M. Soare. Secure Cumulative Reward Maximization in Linear Stochastic Bandits. In Interna- tional Conference on Provable and Practical Security (ProvSec), pages 257-277, 2020.","title":"Secure Cumulative Reward Maximization in Linear Stochastic Bandits","authors":"Ciucanu","year":"2020","venue":"International Conference on Provable and Practical Security (ProvSec)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ciucanu et al., 2020b] R. Ciucanu, P. Lafourcade, M. Lombard-Platet, and M. Soare. Secure Outsourcing of Multi-Armed Bandits. In IEEE International Confer- ence on Trust, Security and Privacy in Computing and Communications (TrustCom), pages 202-209, 2020.","title":"Secure Outsourcing of Multi-Armed Bandits","authors":"Ciucanu","year":"2020","venue":"IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ciucanu et al., 2022] R. Ciucanu, P. Lafourcade, G. Mar- cadet, and M. Soare. SAMBA: A Generic Framework for Secure Federated Multi-Armed Bandits. Journal of Artifi- cial Intelligence Research (JAIR), 73:737-765, 2022.","title":"SAMBA: A Generic Framework for Secure Federated Multi-Armed Bandits","authors":"R Ciucanu, P Lafourcade, G Marcadet, M Soare","year":"2022","venue":"Journal of Artificial Intelligence Research (JAIR)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dubey and Pentland, 2020] A. Dubey and A. Pentland. Differentially-Private Federated Linear Bandits. In Conference on Neural Information Processing Systems (NeurIPS), 2020.","title":"Differentially-Private Federated Linear Bandits","authors":"A Dubey, A Pentland","year":"2020","venue":"Conference on Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dwork and Roth, 2014] C. Dwork and A. Roth. The Algo- rithmic Foundations of Differential Privacy. Foundations and Trends in Theoretical Computer Science, 2014.","title":"The Algorithmic Foundations of Differential Privacy","authors":"C Dwork, A Roth","year":"2014","venue":"Foundations and Trends in Theoretical Computer Science","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Garcelon et al., 2022] E. Garcelon, V. Perchet, and M. Pirotta. Encrypted Linear Contextual Bandit. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.","title":"Encrypted Linear Contextual Bandit","authors":"E Garcelon, V Perchet, M Pirotta","year":"2022","venue":"International Conference on Artificial Intelligence and Statistics (AISTATS)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gentry, 2009] C. Gentry. Fully Homomorphic Encryption Using Ideal Lattices. In Symposium on Theory of Comput- ing (STOC), pages 169-178, 2009.","title":"Fully Homomorphic Encryption Using Ideal Lattices","authors":"C Gentry","year":"2009","venue":"Symposium on Theory of Computing (STOC)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Huang et al., 2021] R. Huang, W. Wu, J. Yang, and C. Shen. Federated Linear Contextual Bandits. In Conference on Neural Information Processing Systems (NeurIPS), 2021.","title":"Federated Linear Contextual Bandits","authors":"R Huang, W Wu, J Yang, C Shen","year":"2021","venue":"Conference on Neural Information Processing Systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kairouz and et al., 2021] P. Kairouz and et al. Advances and Open Problems in Federated Learning. Foundations and Trends in Machine Learning, 14(1-2):1-210, 2021.","title":"Advances and Open Problems in Federated Learning","authors":"P Kairouz","year":"2021","venue":"Foundations and Trends in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2020] T. Li, L. Song, and C. Fragouli. Feder- ated Recommendation System via Differential Privacy. In International Symposium on Information Theory (ISIT), pages 2592-2597, 2020.","title":"Federated Recommendation System via Differential Privacy","authors":"T Li, L Song, C Fragouli","year":"2020","venue":"International Symposium on Information Theory (ISIT)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Marcadet et al., 2022] G. Marcadet, R. Ciucanu, P. Lafour- cade, M. Soare, and S. Amer-Yahia. SAMBA: A System for Secure Federated Multi-Armed Bandits. In IEEE Inter- national Conference on Data Engineering (ICDE), pages 3154-3157, 2022.","title":"SAMBA: A System for Secure Federated Multi-Armed Bandits","authors":"G Marcadet, R Ciucanu, P Lafourcade, M Soare, S Amer-Yahia","year":"2022","venue":"IEEE International Conference on Data Engineering (ICDE)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[National Institute of Standards and Technology, 2001] National Institute of Standards and Technol- ogy. Advanced Encryption Standard (AES). https://doi.org/10.6028/NIST.FIPS.197-upd1, 2001. Accessed: 2023-05-11.","title":"Advanced Encryption Standard","authors":null,"year":"2001","venue":null,"doi":"10.6028/nist.fips.197-upd1","url":"https://doi.org/10.6028/NIST.FIPS.197-upd1,2001","internal_url":null},{"position":15,"raw":"[National Institute of Standards and Technology, 2007] National Institute of Standards and Technol- ogy. Recommendation for BlockCipher Modes of Operation:Galois/Counter Mode (GCM) and GMAC. https://nvlpubs.nist.gov/nistpubs/Legacy/SP/ nistspecialpublication800-38d.pdf, 2007. Accessed: 2023-05-11.","title":"Recommendation for BlockCipher Modes of Operation:Galois/Counter Mode (GCM) and GMAC","authors":null,"year":"2007","venue":null,"doi":null,"url":"https://nvlpubs.nist.gov/nistpubs/Legacy/SP/nistspecialpublication800-38d.pdf","internal_url":null},{"position":16,"raw":"[Paillier, 1999] P. Paillier. Public-Key Cryptosystems Based on Composite Degree Residuosity Classes. In Inter- national Conference on the Theory and Application of Cryptographic Techniques (EUROCRYPT), pages 223- 238, 1999.","title":"Public-Key Cryptosystems Based on Composite Degree Residuosity Classes","authors":"P Paillier","year":"1999","venue":"International Conference on the Theory and Application of Cryptographic Techniques (EUROCRYPT)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Shi and Shen, 2021] C. Shi and C. Shen. Federated Multi- Armed Bandits. In AAAI, pages 9603-9611, 2021.","title":"Federated Multi-Armed Bandits","authors":"C Shi, C Shen","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Shi et al., 2021] C. Shi, C. Shen, and J. Yang. Federated Multi-armed Bandits with Personalization. In Interna- tional Conference on Artificial Intelligence and Statistics (AISTATS), pages 2917-2925, 2021.","title":"Federated Multi-armed Bandits with Personalization","authors":"C Shi, C Shen, J Yang","year":"2021","venue":"International Conference on Artificial Intelligence and Statistics (AISTATS)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sutton and Barto, 2018] R. S. Sutton and A. G. Barto. Re- inforcement Learning: An Introduction. The MIT Press, second edition, 2018.","title":"Reinforcement Learning: An Introduction","authors":"R S Sutton, A G Barto","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tzamaras et al., 2022] S. Tzamaras, R. Ciucanu, M. Soare, and S. Amer-Yahia. FeReD: Federated Reinforcement Learning in the DBMS. In International Conference on Information and Knowledge Management (CIKM), pages 4989-4993, 2022.","title":"FeReD: Federated Reinforcement Learning in the DBMS","authors":"S Tzamaras, R Ciucanu, M Soare, S Amer-Yahia","year":"2022","venue":"International Conference on Information and Knowledge Management (CIKM)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zhu et al., 2021] Z. Zhu, J. Zhu, J. Liu, and Y. Liu. Fed- erated Bandit: A Gossiping Approach. Proceedings of the ACM on Measurement and Analysis of Computing Sys- tems, 5(1), 2021.","title":"Federated Bandit: A Gossiping Approach","authors":"Z Zhu, J Zhu, J Liu, Y Liu","year":"2021","venue":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}