This report summarizes all the MIA experiments (Membership Inference Attacks)
of the Embedding Attack Project, including threat models, experimental setup,
experimental results, findings and discussion. Current results cover the
evaluation of two main MIA strategies (loss-based and embedding-based MIAs) on
6 AI models ranging from Computer Vision to Language Modelling. There are two
ongoing experiments on MIA defense and neighborhood-comparison embedding
attacks. These are ongoing projects.
The current work on MIA and PIA can be summarized into six conclusions: (1)
Amount of overfitting is directly proportional to model's vulnerability; (2)
early embedding layers in the model are less susceptible to privacy leaks; (3)
Deeper model layers contain more membership information; (4) Models are more
vulnerable to MIA if both embeddings and corresponding training labels are
compromised; (5) it is possible to use pseudo-labels to increase the MIA
success; and (6) although MIA and PIA success rates are proportional, reducing
the MIA does not necessarily reduce the PIA.

Embedding Attack Project 的 MIA 实验结果总结，包括威胁模型、实验设置、实验结果、发现和讨论。当前结果涵盖了对 6 个 AI 模型的两种主要 MIA 策略（基于损失和基于嵌入）的评估，涵盖了从计算机视觉到语言建模的范围。六个结论总结了关于 MIA 和 PIA 的当前研究成果。