Privacy-Preserving Federated Learning Using Homomorphic Encryption
Source abstract
Abstract
Federated learning (FL) is a machine learning technique that enables distributed devices to train a learning model collaboratively without sharing their local data. FL-based systems can achieve much stronger privacy preservation since the distributed devices deliver only local model parameters trained with local data to a centralized server. However, there exists a possibility that a centralized server or attackers infer/extract sensitive private information using the structure and parameters of local learning models. We propose employing homomorphic encryption (HE) scheme that can directly perform arithmetic operations on ciphertexts without decryption to protect the model parameters. Using the HE scheme, the proposed privacy-preserving federated learning (PPFL) algorithm enables the centralized server to aggregate encrypted local model parameters without decryption. Furthermore, the proposed algorithm allows each node to use a different HE private key in the same FL-based system using a distributed cryptosystem. The performance analysis and evaluation of the proposed PPFL algorithm are conducted in various cloud computing-based FL service scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data · Cryptography and Data Security · Stochastic Gradient Optimization Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju 61005, Korea
AI Graduate School, Gwangju Institute of Science and Technology (GIST), Gwangju 61005, Korea
Funding
Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT))
References (25)
Show source-provided references
1. McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017, January 20–22). Communication-efficient learning of deep networks from decentralized data. Proceedings of the International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA.
2. Privacy-preserving deep learning via additively homomorphic encryption
3. Hitaj, B., Ateniese, G., and Perez-Cruz, F. (November, January 30). Deep models under the GAN: Information leakage from collaborative deep learning. Proceedings of the ACM SIGSAC Conference on Computer and Communications Security, Dallas, TX, USA.
4. A survey on federated learning10.1016/j.knosys.2021.106775 ↗
5. Federated learning for internet of things: Recent advances, taxonomy, and open challenges10.1109/COMST.2021.3090430 ↗
6. Privacy-preserving multiobjective sanitization model in 6G IoT environments10.1109/JIOT.2020.3032896 ↗
7. Li, T., Hu, S., Beirami, A., and Smith, V. (2021, January 18–24). Ditto: Fair and robust federated learning through personalization. Proceedings of the International Conference on Machine Learning, Virtual.
8. Lin, F.P.C., Hosseinalipour, S., Azam, S.S., Brinton, C.G., and Michelusi, N. (2021). Semi-decentralized federated learning with cooperative D2D local model aggregations. IEEE J. Sel. Areas Commun., in press.10.1109/JSAC.2021.3118344 ↗
9. Federated machine learning: Concept and applications10.1145/3339474 ↗
10. A homomorphic-encryption-based vertical federated learning scheme for rick management10.2298/CSIS190923022O ↗
11. Zhang, C., Li, S., Xia, J., Wang, W., Yan, F., and Liu, Y. (2020, January 15–17). Batchcrypt: Efficient homomorphic encryption for cross-silo federated learning. Proceedings of the 2020 USENIX Annual Technical Conference (USENIXATC 20), Online.
12. Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., Papadopoulos, D., and Yang, Q. (2021). Secureboost: A lossless federated learning framework. IEEE Intell. Syst., in press.10.1109/MIS.2021.3082561 ↗
13. Shokri, R., and Shmatikov, V. (2015, January 12–16). Privacy-preserving deep learning. Proceedings of the ACM SIGSAC Conference on Computer and Communications Security, Denver, CO, USA.10.1145/2810103.2813687 ↗
14. Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H.B., Patel, S., Ramage, D., Segal, A., and Seth, K. (November, January 30). Practical secure aggregation for privacy-preserving machine learning. Proceedings of the ACM SIGSAC Conference on Computer and Communications Security, Dallas, TX, USA.
15. Verifynet: Secure and verifiable federated learning10.1109/TIFS.2019.2929409 ↗
16. Fang, H., and Qian, Q. (2021). Privacy Preserving Machine Learning with Homomorphic Encryption and Federated Learning. Future Internet, 13.10.3390/fi13040094 ↗
17. How to share a secret10.1145/359168.359176 ↗
18. A survey on transfer learning10.1109/TKDE.2009.191 ↗
19. Paillier, P. (1999, January 14–18). Public-key cryptosystems based on composite degree residuosity classes. Proceedings of the International Conference on the Theory and Application of Cryptology and Information Security, Singapore.
20. Gentry, C. (June, January 31). Fully homomorphic encryption using ideal lattices. Proceedings of the Annual ACM Symposium on Theory of Computing, Bethesda, MD, USA.
21. An efficient privacy-preserving outsourced calculation toolkit with multiple keys10.1109/TIFS.2016.2573770 ↗
22. Katz, J., and Lindell, Y. (2020). Introduction to Modern Cryptography, CRC Press.10.1201/9781351133036 ↗
23. Efficient and privacy-preserving outsourced calculation of rational numbers10.1109/TDSC.2016.2536601 ↗
24. Barker, E., Barker, E., Burr, W., Polk, W., and Smid, M. (2006). Recommendation for Key Management: Part 1: General, National Institute of Standards and Technology, Technology Administration.10.6028/NIST.SP.800-57p1r2006 ↗
25. Bresson, E., Catalano, D., and Pointcheval, D. (December, January 30). A simple public-key cryptosystem with a double trapdoor decryption mechanism and its applications. Proceedings of the International Conference on the Theory and Application of Cryptology and Information Security, Taipei, Taiwan.