A Comprehensive Analysis of Factors Impacting Membership Inference

Daniel Dealcala, Gonzalo Mancera, Aythami Morales, Julian Fierrez, Ruben Tolosana, Javier Ortega-Garcia; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 3585-3593

We analyze various factors affecting the proper functioning of MIA and MINT two research lines aimed at detecting data used for training. The difference between these lines lies in the environmental conditions while the fundamental bases are similar for both. As evident in the literature this detection task is far from straightforward and poses an ongoing challenge for the scientific community. Specifically in this work we conclude that factors such as the number of times data passes through the original network the loss function or dropout significantly impact detection outcomes. Therefore it is crucial to consider them when developing these methods and during the training of any neural network both to avoid (MIA) and to enhance (MINT) this detection. We evaluate the AdaFace facial recognition model using five databases with over 22 million images modifying the different factors under analysis and defining a suitable protocol for their examination. State-of-the-art accuracy reaching up to 87% is achieved surpassing existing methods.