HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning

By Runhua Xu, Nathalie Baracaldo, Yi Zhou, Ali Anwar, Heiko Ludwig. 2019

321 citations recorded by the source corpus.

Federated learning has emerged as a promising approach for collaborative and privacy-preserving learning. Participants in a federated learning process cooperatively train a model by exchanging model parameters instead of the actual training data, which they might want to keep private. However, parameter interaction and the resulting model still might disclose information about the training data used. To address these privacy concerns, several approaches have been proposed based on differential privacy and secure multiparty computation (SMC), among others. They often result in large communication overhead and slow training time. In this paper, we propose HybridAlpha, an approach for privacy-preserving federated learning employing an SMC protocol based on functional encryption. This protocol is simple, efficient and resilient to participants dropping out. We evaluate our approach regarding the training time and data volume exchanged using a federated learning process to train a CNN on the MNIST data set. Evaluation against existing crypto-based SMC solutions shows that HybridAlpha can reduce the training time by 68% and data transfer volume by 92% on average while providing the same model performance and privacy guarantees as the existing solutions.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qiang Yang
2. Murali Annavaram
3. Chaoyang He
4. Bingsheng He
5. Qinbin Li
6. Yang Liu
7. Jiankun Hu
8. Yanming Zhu

Citations in the corpus

• FedML: A Research Library and Benchmark for Federated Machine Learning (2020, methodology): “…robust [13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 22], and proposing methods such as differential privacy (DP) and secure multiparty computation (SMPC) to protect privacy [25, 26, 27, 28, 29, 30, 31, 32, 33] (see Table 8 in the appendix for a taxonomy of the federated learning literature).”
• IBM Federated Learning: an Enterprise Framework White Paper V0.1 (2020, methodology): “Methods of creating differentially private noise or secure multi-party computation are used to meet these privacy requirements [8, 13, 31, 33].”
• Federated Learning on Non-IID Data: A Survey (2021, methodology): “Besides HE and DP based protection methods, other techniques [146, 77, 152] have also been used, and integrating secure aggregation protocol with a double masking technique [6] is a very popular approach.”
• A Comprehensive Survey of Privacy-preserving Federated Learning (2021, methodology): “• In the FL, the intermediate weights or gradients communicated between participants and the aggregator may reveal sensitive information about the participants’ training datasets, as shown in References [96, 137, 198, 212].”
• A Survey on federated learning* (2020, methodology): “Then the efficient HybridAlpha [48] emerged at the right moment, which combined functional encryption with SMC protocol to achieve the highly-performance model without privacy sacrifice.”
• Differential Privacy for Deep and Federated Learning: A Survey (2022, methodology): “The authors use functional encryption (FE) [128] to protect the communication between clients and the server.”
• Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges (2020, methodology): “A malicious end-device and aggregation server can infer end-devices sensitive information using their local learning model updates [26], [40]. of privacy leakage, we can use additive homomorphic encryption in federated learning [53], [54].”
• A review of applications in federated learning (2020, background): “Moreover, Yang, Zhang, Ye, Li and C.-Z. Xu (2019) leveraged FL to transactions owned by different banks in order to detect credit card fraud efficiently, which is also a significant contribution to financial field.”
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019, background): “other, and an FLS can adopt multiple methods to enhance the privacy guarantees [60], [78], [189].”
• Privacy Preserving Machine Learning with Homomorphic Encryption and Federated Learning (2021, methodology): “Zhou et al. proposed using differential privacy to protect privacy in machine learning, and SMC was used to reduce the noise caused by differential privacy [44,45].”