A Comprehensive Analysis of Information Leakage in Deep Transfer Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Transfer LearningSimilar Papers 제목 키워드 기반
StyleStegan: Leak-free Style Transfer Based on Feature Steganography
In modern social networks, existing style transfer methods suffer from a serious content leakage issue, which hampers the ability to achieve serial and reversible stylization, thereby hindering the further propagation of…
Image SteganographySSIMStyle TransferInformation Theoretic Evaluation of Privacy-Leakage, Interpretability, and Transferability for Trustworthy AI
In order to develop machine learning and deep learning models that take into account the guidelines and principles of trustworthy AI, a novel information theoretic trustworthy AI framework is introduced. A unified approa…
Heart Rate VariabilityPrivacy PreservingPATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing
Language models (LMs) may memorize personally identifiable information (PII) from training data, enabling adversaries to extract it during inference. Existing defense mechanisms such as differential privacy (DP) reduce t…
Data Leakage in Automotive Perception: Practitioners' Insights
Data leakage is the inadvertent transfer of information between training and evaluation datasets that poses a subtle, yet critical, risk to the reliability of machine learning (ML) models in safety-critical systems such …
Q-Align: Alleviating Attention Leakage in Zero-Shot Appearance Transfer via Query-Query Alignment
We observe that zero-shot appearance transfer with large-scale image generation models faces a significant challenge: Attention Leakage. This challenge arises when the semantic mapping between two images is captured by t…
Image Generation