Similarity Distribution based Membership Inference Attack on Person Re-identification

arXiv:2211.15918v1 Announce Type: cross
Abstract: While person Re-identification (Re-ID) has progressed rapidly due to its wide real-world applications, it also causes severe risks of leaking personal information from training data. Thus, this paper focuses on quantifying this risk by membership inference (MI) attack. Most of the existing MI attack algorithms focus on classification models, while Re-ID follows a totally different training and inference paradigm. Re-ID is a fine-grained recognition task with complex feature embedding, and model outputs commonly used by …

abstract algorithms applications arxiv cs.cr cs.cv data distribution focus identification inference information paper person personal information risk risks training training data type world