N Carlini, S Chien, M Nasr, S Song… - … IEEE Symposium on …, 2022 - ieeexplore.ieee.org
A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training …
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 …
We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to …
Modern neural language models that are widely used in various NLP tasks risk memorizing sensitive information from their training data. Understanding this memorization is important …
Synthetic data has been advertised as a silver-bullet solution to privacy-preserving data publishing that addresses the shortcomings of traditional anonymisation techniques. The …
C Liu, B Chen, W Shao, C Zhang… - IEEE Internet of …, 2024 - ieeexplore.ieee.org
The advent of the Internet of Things (IoT) has brought forth an era of unprecedented connectivity, with an estimated 80 billion smart devices expected to be in operation by the …
Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific …
Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference …
S Neel, P Chang - arXiv preprint arXiv:2312.06717, 2023 - arxiv.org
This is the first survey of the active area of AI research that focuses on privacy issues in Large Language Models (LLMs). Specifically, we focus on work that red-teams models to …