2020/05/18 by Zhuoran Ma, Jianfeng Ma, Ma, Zhuoran +12 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning #Adversary #Artificial intelligence #Computer science #Computer security #Covert #Cryptography #Cryptography and Security (cs.CR) #Domain (mathematical analysis) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine learning #Oblivious transfer #Privacy-Preserving Technologies in Data #Security domain #Theoretical computer science #Transfer of learning #Verifiable secret sharing #cs.CR
paper · pdf · doi:10.48550/arxiv.2005.08997
published in arXiv (Cornell University) (Cornell University)
arxiv created 2020/05/18 · openalex publication_date 2020/05/18 · arxiv updated 2020/05/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
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.