M^4I: Multi-modal Models Membership Inference. (arXiv:2209.06997v1 [cs.LG])

Web: http://arxiv.org/abs/2209.06997

With the development of machine learning techniques, the attention of
research has been moved from single-modal learning to multi-modal learning, as
real-world data exist in the form of different modalities. However, multi-modal
models often carry more information than single-modal models and they are
usually applied in sensitive scenarios, such as medical report generation or
disease identification. Compared with the existing membership inference against
machine learning classifiers, we focus on the problem that the input and output
of the multi-modal models …