Abstract
In federated learning, a parameter server needs to aggregate user gradients and a user needs the privacy of their individual gradients. Among all the possible solutions, additive homomorphic encryption is a natural choice. As users may drop out during a federated learning process, and an adversary could corrupt users and the parameter server, a dropout-resilient scheme with distributed key generation is required. We present a lattice based distributed threshold additive homomorphic encryption scheme with provable security that could be used in the federated learning. The evaluation shows that our proposal has a lower communication overhead among all lattice based proposals when the number of users in FL exceeds 26.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., Chu, A., Goodfellow, I., McMahan, H.B., Mironov, I., Talwar, K., Zhang, L.: Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. pp. 308–318. CCS 2016, Association for Computing Machinery, New York, NY, USA (2016). https://doi.org/10.1145/2976749.2978318
Al-Rubaie, M., Chang, J.M.: Reconstruction attacks against mobile-based continuous authentication systems in the cloud. IEEE Trans. Inf. Forensics Secur. 11(12), 2648–2663 (2016). https://doi.org/10.1109/TIFS.2016.2594132
Albrecht, M.,et al.: Homomorphic encryption security standard. Technical report, HomomorphicEncryption.org, Toronto, Canada, November 2018
Asharov, G., Jain, A., López-Alt, A., Tromer, E., Vaikuntanathan, V., Wichs, D.: Multiparty computation with low communication, computation and interaction via threshold FHE. In: Pointcheval, D., Johansson, T. (eds.) EUROCRYPT 2012. LNCS, vol. 7237, pp. 483–501. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-29011-4_29
Bendlin, R., Damgård, I.: Threshold decryption and zero-knowledge proofs for lattice-based cryptosystems. In: Micciancio, D. (ed.) TCC 2010. LNCS, vol. 5978, pp. 201–218. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-11799-2_13
Bonawitz, K., et al.: Practical secure aggregation for privacy-preserving machine learning. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pp. 1175–1191. CCS 2017, Association for Computing Machinery, New York, NY, USA (2017). https://doi.org/10.1145/3133956.3133982
Boneh, D., Gennaro, R., Goldfeder, S., Jain, A., Kim, S., Rasmussen, P.M.R., Sahai, A.: Threshold cryptosystems from threshold fully homomorphic encryption. In: Shacham, H., Boldyreva, A. (eds.) CRYPTO 2018. LNCS, vol. 10991, pp. 565–596. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-96884-1_19
Brakerski, Z.: Fully homomorphic encryption without modulus switching from classical GapSVP. In: Safavi-Naini, R., Canetti, R. (eds.) CRYPTO 2012. LNCS, vol. 7417, pp. 868–886. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-32009-5_50
Bresson, E., Catalano, D., Pointcheval, D.: A simple public-key cryptosystem with a double trapdoor decryption mechanism and its applications. In: Laih, C.-S. (ed.) ASIACRYPT 2003. LNCS, vol. 2894, pp. 37–54. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-40061-5_3
Chen, H., Dai, W., Kim, M., Song, Y.: Efficient multi-key homomorphic encryption with packed ciphertexts with application to oblivious neural network inference. In: Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security. p. 395–412. CCS 2019, Association for Computing Machinery, New York, NY, USA (2019). https://doi.org/10.1145/3319535.3363207
Damgård, I., Jurik, M.: A generalisation, a simplification and some applications of Paillier’s probabilistic public-key system. In: Kim, K. (ed.) PKC 2001. LNCS, vol. 1992, pp. 119–136. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-44586-2_9
Di, C., Leye, W., Kai, C., Qiang, Y.: Secure federated matrix factorization. In: FML 2019 : The 1st International Workshop on Federated Machine Learning for User Privacy and Data Confidentiality (2019)
Fan, J., Vercauteren, F.: Somewhat practical fully homomorphic encryption. Cryptology ePrint Archive, Report 2012/144 (2012). https://eprint.iacr.org/2012/144
Fereidooni, H., et al.: Secure aggregation for private federated learning. In: 2021 IEEE Security and Privacy Workshops (SPW), pp. 56–62 (2021). https://doi.org/10.1109/SPW53761.2021.00017
Fredrikson, M., Jha, S., Ristenpart, T.: Model inversion attacks that exploit confidence information and basic countermeasures. In: Proceedings of the 22Nd ACM SIGSAC Conference on Computer and Communications Security, pp. 1322–1333. CCS 2015, ACM, New York, NY, USA (2015). https://doi.org/10.1145/2810103.2813677
Froelicher, D., et al.: Scalable privacy-preserving distributed learning. Proc. Priv. Enhanc. Technol. 2021(2), 323–347 (2021)
Geiping, J., Bauermeister, H., Drge, H., Moeller, M.: Inverting gradients - how easy is it to break privacy in federated learning? (2020). http://arxiv.org/abs/2003.14053v1
Gennaro, R., Jarecki, S., Krawczyk, H., Rabin, T.: Secure distributed key generation for discrete-log based cryptosystems. In: Stern, J. (ed.) EUROCRYPT 1999. LNCS, vol. 1592, pp. 295–310. Springer, Heidelberg (1999). https://doi.org/10.1007/3-540-48910-X_21
Herranz, J., Hofheinz, D., Kiltz, E.: Some (in)sufficient conditions for secure hybrid encryption. Inf. Comput. 208(11), 1243–1257 (010). https://doi.org/10.1016/j.ic.2010.07.002
Hosseini, E., Khisti, A.: Secure aggregation in federated learning via multiparty homomorphic encryption. In: 2021 IEEE Globecom Workshops (GC Wkshps), pp. 1–6 (2021). https://doi.org/10.1109/GCWkshps52748.2021.9682053
Jiang, Z.L., Guo, H., Pan, Y., Liu, Y., Wang, X., Zhang, J.: Secure neural network in federated learning with model aggregation under multiple keys. In: 2021 8th IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)/2021 7th IEEE International Conference on Edge Computing and Scalable Cloud (EdgeCom), pp. 47–52. IEEE (2021)
Kim, E., Jeong, J., Yoon, H., Kim, Y., Cho, J., Cheon, J.H.: How to securely collaborate on data: decentralized threshold he and secure key update. IEEE Access 8, 191319–191329 (2020). https://doi.org/10.1109/ACCESS.2020.3030970
Li, Y., Li, H., Xu, G., Huang, X., Lu, R.: Efficient privacy-preserving federated learning with unreliable users. IEEE Internet Things J. 1 (2021). https://doi.org/10.1109/JIOT.2021.3130115
Liu, Y., et al.: Boosting privately: federated extreme gradient boosting for mobile crowdsensing. In: 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS), pp. 1–11 (2020). https://doi.org/10.1109/ICDCS47774.2020.00017
Lyubashevsky, V., Peikert, C., Regev, O.: On ideal lattices and learning with errors over rings. In: Gilbert, H. (ed.) EUROCRYPT 2010. LNCS, vol. 6110, pp. 1–23. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-13190-5_1
Ma, J., Naas, S.A., Sigg, S., Lyu, X.: Privacy-preserving federated learning based on multi-key homomorphic encryption. Int. J. Intell. Syst. (2022)
McMahan, H.B., Moore, E., Ramage, D., y Arcas, B.A.: Federated learning of deep networks using model averaging. CoRR abs/1602.05629 (2016). http://arxiv.org/abs/1602.05629
Mo, F., Haddadi, H., Katevas, K., Marin, E., Perino, D., Kourtellis, N.: PPFL: privacy-preserving federated learning with trusted execution environments (2021). https://doi.org/10.48550/ARXIV.2104.14380, https://arxiv.org/abs/2104.14380
Mouchet, C., Troncoso-Pastoriza, J., Bossuat, J.P., Hubaux, J.P.: Multiparty homomorphic encryption from ring-learning-with-errors. Cryptology ePrint Archive, Report 2020/304 (2020). https://ia.cr/2020/304
Paillier, P.: Public-key cryptosystems based on composite degree residuosity classes. In: Stern, J. (ed.) EUROCRYPT 1999. LNCS, vol. 1592, pp. 223–238. Springer, Heidelberg (1999). https://doi.org/10.1007/3-540-48910-X_16
Pedersen, T.P.: A threshold cryptosystem without a trusted party. In: Davies, D.W. (ed.) EUROCRYPT 1991. LNCS, vol. 547, pp. 522–526. Springer, Heidelberg (1991). https://doi.org/10.1007/3-540-46416-6_47
Sav, S., et al.: POSEIDON: privacy-preserving federated neural network learning. arXiv preprint arXiv:2009.00349 (2020)
Tian, H., Zhang, F., Shao, Y., Li, B.: Secure linear aggregation using decentralized threshold additive homomorphic encryption for federated learning (2021). https://doi.org/10.48550/ARXIV.2111.10753, https://arxiv.org/abs/2111.10753
Truex, S., et al.: A hybrid approach to privacy-preserving federated learning. In: Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security, pp. 1–11. AISec 2019, Association for Computing Machinery, New York, NY, USA (2019). https://doi.org/10.1145/3338501.3357370
Urban, A., Rambaud, M.: Share & shrink: Ad-hoc threshold FHE with short ciphertexts and its application to almost-asynchronous MPC. Cryptology ePrint Archive, Paper 2022/378 (2022). https://eprint.iacr.org/2022/378
Yin, H., Mallya, A., Vahdat, A., Alvarez, J.M., Kautz, J., Molchanov, P.: See through gradients: Image batch recovery via gradinversion (2021). http://arxiv.org/abs/2104.07586
Zhang, F., Zhang, Z., Guan, P.: ECC2: error correcting code and elliptic curve based cryptosystem. Inf. Sci. 526, 301–320 (2020). https://doi.org/10.1016/j.ins.2020.03.069, https://www.sciencedirect.com/science/article/pii/S0020025520302498
Zhao, B., Mopuri, K.R., Bilen, H.: IDLG: Improved deep leakage from gradients (2020). http://arxiv.org/abs/2001.02610
Zhu, H., Wang, R., Jin, Y., Liang, K., Ning, J.: Distributed additive encryption and quantization for privacy preserving federated deep learning. Neurocomputing 463, 309–327 (2021)
Zhu, L., Liu, Z., Han, S.: Deep leakage from gradients (2019). http://arxiv.org/abs/1906.08935
Acknowledgement
Thanks to Huawei Noah’s Ark Lab for funding this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Tian, H., Wen, Y., Zhang, F., Shao, Y., Li, B. (2022). A Distributed Threshold Additive Homomorphic Encryption for Federated Learning with Dropout Resiliency Based on Lattice. In: Chen, X., Shen, J., Susilo, W. (eds) Cyberspace Safety and Security. CSS 2022. Lecture Notes in Computer Science, vol 13547. Springer, Cham. https://doi.org/10.1007/978-3-031-18067-5_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-18067-5_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18066-8
Online ISBN: 978-3-031-18067-5
eBook Packages: Computer ScienceComputer Science (R0)