SeqMIA: Sequential-Metric Based Membership Inference Attack
Published in Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security (CCS), 2024
SeqMIA utilizes a sequence of distilled models to capture training dynamics, enabling precise membership inference.
Recommended citation: H Li, Z Li, S Wu, C Hu, Y Ye, M Zhang, D Feng, Y Zhang. (2024). "SeqMIA: Sequential-Metric Based Membership Inference Attack." ACM CCS.