Secure and Efficient Federated Transfer Learning

By Shreya Sharma, Chaoping Xing, Yang Liu, Yan Kang. 2019

96 citations recorded by the source corpus.

Machine Learning models require a vast amount of data for accurate training. In reality, most data is scattered across different organizations and cannot be easily integrated under many legal and practical constraints. Federated Transfer Learning (FTL) was introduced in [1] to improve statistical models under a data federation that allow knowledge to be shared without compromising user privacy, and enable complementary knowledge to be transferred in the network. As a result, a target-domain party can build more flexible and powerful models by leveraging rich labels from a source-domain party. However, the excessive computational overhead of the security protocol involved in this model rendered it impractical. In this work, we aim towards enhancing the efficiency and security of existing models for practical collaborative training under a data federation by incorporating Secret Sharing (SS). In literature, only the semi-honest model for Federated Transfer Learning has been considered. In this paper, we improve upon the previous solution, and also allow malicious players who can arbitrarily deviate from the protocol in our FTL model. This is much stronger than the semi-honest model where we assume that parties follow the protocol precisely. We do so using the one of the practical MPC protocol called SPDZ, thus our model can be efficiently extended to any number of parties even in the case of a dishonest majority. In addition, the models evaluated in our setting significantly outperform the previous work, in terms of both runtime and communication cost. A single iteration in our model executes in 0.8 seconds for the semi-honest case and 1.4 seconds for the malicious case for 500 samples, as compared to 35 seconds taken by the previous implementation.

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. Yang Liu
2. Jiankun Hu
3. Yanming Zhu
4. Xuefei Yin
5. Qiang Yang
6. Tianjian Chen
7. Yan Kang
8. Azzam Mourad

Citations in the corpus

• FATE: An Industrial Grade Platform for Collaborative Learning With Data Protection (2021, methodology): “In (Sharma et al., 2019) security is enhanced by SPDZ algorithm.”
• Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues (2020, background): “[30] enhance the security of existing federated transfer learning models under malicious setting where some players could arbitrarily deviate from the predefined protocol.”
• Federated Learning for Internet of Things: A Comprehensive Survey (2021, background): “on the combined updates from learning participants, the aggregation server can perform model learning to find the global update by minimizing a loss function [33].”
• A Comprehensive Survey of Privacy-preserving Federated Learning (2021, methodology): “Secret sharing has been used in many FL frameworks to achieve privacy preservation [38, 59, 113, 126, 157, 169, 198, 224].”
• Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems (2021, background): “In [66], the authors extend and improve upon [65] in two ways (1) reducing the overhead of”
• Vertical Federated Learning: Concepts, Advances, and Challenges (2022, methodology): “The follow-up work [82] leverages SPDZ [86] to enhance the effi-ciency of SFTL further.”
• Federated Learning for Smart Healthcare: A Survey (2021, methodology): “By using a transfer learning method, feature values are calculated from different feature spaces to the same representation which is exploited to train local datasets [22].”