Differentially private ML is hard. Even basic "solved" tasks in the non-private setting are very hard to do with privacy. Figure from a nice paper by @sohamde_ @LeonardBerrada et al (
https://
arxiv.org/abs/2204.13650), showing SOTA results on CIFAR10.. 60-80%, versus 99%+ non-privately 2/n

→ View original post on X — @thegautamkamath,