Differentially Private Representation Learning via Image Captioning

arXiv:2403.02506v1 Announce Type: cross
Abstract: Differentially private (DP) machine learning is considered the gold-standard solution for training a model from sensitive data while still preserving privacy. However, a major barrier to achieving this ideal is its sub-optimal privacy-accuracy trade-off, which is particularly visible in DP representation learning. Specifically, it has been shown that under modest privacy budgets, most models learn representations that are not significantly better than hand-crafted features. In this work, we show that effective DP representation learning can …

abstract accuracy arxiv captioning cs.cv cs.lg data image machine machine learning major privacy representation representation learning solution standard trade trade-off training type via