2020/09/04 by Cen Chen, Chen, Cen, Bingzhe Wu +7 · 12 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Computer security #Data science #Deep learning #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Information leakage #Leakage (economics) #Machine Learning (cs.LG) #Machine learning #Privacy-Preserving Technologies in Data #Public domain #Transfer of learning #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.2009.01989
published in arXiv (Cornell University) (Cornell University) · 10 pages
arxiv created 2020/09/04 · openalex publication_date 2020/09/04 · arxiv updated 2020/09/07 · openalex created_date 2020/09/11 · openalex updated_date 2026/08/08
Transfer learning is widely used for transferring knowledge from a source domain to the target domain where the labeled data is scarce. Recently, deep transfer learning has achieved remarkable progress in various applications. However, the source and target datasets usually belong to two different organizations in many real-world scenarios, potential privacy issues in deep transfer learning are posed. In this study, to thoroughly analyze the potential privacy leakage in deep transfer learning, we first divide previous methods into three categories. Based on that, we demonstrate specific threats that lead to unintentional privacy leakage in each category. Additionally, we also provide some solutions to prevent these threats. To the best of our knowledge, our study is the first to provide a thorough analysis of the information leakage issues in deep transfer learning methods and provide potential solutions to the issue. Extensive experiments on two public datasets and an industry dataset are conducted to show the privacy leakage under different deep transfer learning settings and defense solution effectiveness.