VerifyTL: Secure and Verifiable Collaborative Transfer Learning
This addresses the need for secure collaborative learning in sensitive domains where data sharing is risky, though it appears incremental as an extension of existing secure computation techniques to transfer learning.
The paper tackles the problem of secure two-way transfer learning between potentially untrusted datasets, introducing VerifyTL which provides privacy guarantees and verification against covert adversaries. Experimental results on real-world datasets show VerifyTL achieves significant performance gains over existing secure learning schemes.
Getting access to labelled datasets in certain sensitive application domains can be challenging. Hence, one often resorts to transfer learning to transfer knowledge learned from a source domain with sufficient labelled data to a target domain with limited labelled data. However, most existing transfer learning techniques only focus on one-way transfer which brings no benefit to the source domain. In addition, there is the risk of a covert adversary corrupting a number of domains, which can consequently result in inaccurate prediction or privacy leakage. In this paper we construct a secure and Verifiable collaborative Transfer Learning scheme, VerifyTL, to support two-way transfer learning over potentially untrusted datasets by improving knowledge transfer from a target domain to a source domain. Further, we equip VerifyTL with a cross transfer unit and a weave transfer unit employing SPDZ computation to provide privacy guarantee and verification in the two-domain setting and the multi-domain setting, respectively. Thus, VerifyTL is secure against covert adversary that can compromise up to n-1 out of n data domains. We analyze the security of VerifyTL and evaluate its performance over two real-world datasets. Experimental results show that VerifyTL achieves significant performance gains over existing secure learning schemes.