Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds

arXiv:2404.02866v1 Announce Type: cross
Abstract: Protecting privacy during inference with deep neural networks is possible by adding noise to the activations in the last layers prior to the final classifiers or other task-specific layers. The activations in such layers are known as "features" (or, less commonly, as "embeddings" or "feature embeddings"). The added noise helps prevent reconstruction of the inputs from the noisy features. Lower bounding the variance of every possible unbiased estimator of the inputs quantifies the confidentiality arising …

arxiv confidentiality cs.cr cs.cy cs.lg feature features networks neural networks noise privacy protecting stat.ml task