Unintended memorisation of unique features in neural networks. (arXiv:2205.10079v1 [cs.LG])

Neural networks pose a privacy risk due to their propensity to memorise and
leak training data. We show that unique features occurring only once in
training data are memorised by discriminative multi-layer perceptrons and
convolutional neural networks trained on benchmark imaging datasets. We design
our method for settings where sensitive training data is not available, for
example medical imaging. Our setting knows the unique feature, but not the
training data, model weights or the unique feature's label. We develop a …

arxiv features networks neural networks