SplitAUM: Auxiliary Model-Based Label Inference Attack Against Split Learning

Split learning has emerged as a practical and efficient privacy-preserving distributed machine learning paradigm. Understanding the privacy risks of split learning is critical for its application in privacy-sensitive scenarios. However, previous attacks against split learning generally depended on unduly strong assumptions or non-standard settings advantageous to the attacker. This paper proposes a novel auxiliary model-based label inference attack framework against learning, named SplitAUM. SplitAUM first builds an auxiliary model on the client side using intermediate representations of the cut layer and a small number of dummy labels. Then, the learning regularization objective is carefully designed to train the auxiliary model and transfer the knowledge of the server model to the client. Finally, SplitAUM uses the auxiliary model output on local data to infer the server’s privacy label. In addition, to further improve the attack effect, we use semi-supervised clustering to initialize the dummy labels of the auxiliary model. Since SplitAUM relies only on auxiliary models, it is highly scalable. We conduct extensive experiments on three different categories of datasets, comparing four typical attacks. Experimental results demonstrate that SplitAUM can effectively infer privacy labels and outperform existing attack frameworks in challenging yet practical scenarios. We hope our work paves the way for future analyses of the security of split learning.