AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigation
University of Connecticut（康涅狄格大学）；Courant Institute, New York University（纽约大学柯朗数学科学研究所）；Robert H. Smith School of Business, University of Maryland（马里兰大学罗伯特·H·史密斯商学院）；School of Information, University of California（加州大学信息学院）
Ying Chen, Jiajing Chen, Yijie Weng, ChiaHua Chang, Dezhi Yu, Guanbiao Lin
Membership inference attacks have emerged as a significant privacy concern in the training of deep learning models, where attackers can infer whether a data point was part of the training set based on the model's outputs. To address this challenge, we propose a novel defense mechanism, AdaMixup. AdaMixup employs adaptive mixup techniques to enhance the model's robustness against membership inference attacks by dynamically adjusting the mixup strategy during training. This method not only improves the model's privacy protection but also maintains high performance. Experimental results across multiple datasets demonstrate that AdaMixup significantly reduces the risk of membership inference attacks while achieving a favorable trade-off between defensive efficiency and model accuracy. This research provides an effective solution for data privacy protection and lays the groundwork for future advancements in mixup training methods.
When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training
Nanjing University of Science and Technology（南京理工大学）；The University of Newcastle（纽卡斯尔大学）；Southeast University（东南大学）；Sungkyunkwan University（成均馆大学）；The University of Western Australia（西澳大学）
