research
∙
09/09/2023
Reverse-Engineering Decoding Strategies Given Blackbox Access to a Language Generation System
Neural language models are increasingly deployed into APIs and websites ...
share
research
∙
05/15/2023
Privacy Auditing with One (1) Training Run
We propose a scheme for auditing differentially private machine learning...
research
∙
01/30/2023
Extracting Training Data from Diffusion Models
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion ha...
research
∙
09/29/2022
