[1A] DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
▶[1A] DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing — a 2021 PETS / HotPETS 2021 security conference talk on privacy, ai-ml (17:42 min). Watch the full video, indexed free on the Breach Arc Archive.
▶ Watch video on YouTube