← Search

Andrew Paverd

2 accepted papers

2023

Bayesian Estimation of Differential Privacy

ICML 2023poster

Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, because these guarantees hold with respect to unrealistic adversaries, the protection afforded against practical attacks is typically much better. An emerging strand of work…

2021

Grey-box Extraction of Natural Language Models

ICML 2021spotlight

Model extraction attacks attempt to replicate a target machine learning model by querying its inference API. State-of-the-art attacks are learning-based and construct replicas by supervised training on the target model’s predictions, but an emerging class of attacks exploit algebraic properties to o…

Cited by 38SourcePDFScholar