The newly emerged machine learning (eg, deep learning) methods have become a strong driving force to revolutionize a wide range of industries, such as smart healthcare, financial …
It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary can …
Understanding to what extent neural networks memorize training data is an intriguing question with practical and theoretical implications. In this paper we show that in some …
Y Zhou, E Nezhadarya, J Ba - Advances in Neural …, 2022 - proceedings.neurips.cc
Dataset distillation aims to learn a small synthetic dataset that preserves most of the information from the original dataset. Dataset distillation can be formulated as a bi-level …
J Ye, A Maddi, SK Murakonda… - Proceedings of the …, 2022 - dl.acm.org
How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this …
Membership inference is one of the simplest privacy threats faced by machine learning models that are trained on private sensitive data. In this attack, an adversary infers whether a …
Although large language models (LLMs) are widely deployed, the data used to train them is rarely disclosed. Given the incredible scale of this data, up to trillions of tokens, it is all but …
Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a …
Deep Learning (DL) algorithms based on artificial neural networks have achieved remarkable success and are being extensively applied in a variety of application domains …