Related papers: On the Privacy Risks of Model Explanations

Bias in data can have unintended consequences that propagate to the design, development, and deployment of machine learning models. In the financial services sector, this can result in discrimination from certain financial instruments and…

Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing…

The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…

Machine unlearning (MU) has emerged as a key mechanism for ensuring data privacy and regulatory compliance by enabling models to forget specific training samples. However, recent studies have shown that the removal of data can inadvertently…

The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the training set can be reconstructed directly from model parameters.…

Hierarchical text classification consists in classifying text documents into a hierarchy of classes and sub-classes. Although artificial neural networks have proved useful to perform this task, unfortunately they can leak training data…

Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query…

As machine learning becomes more widely used, the need to study its implications in security and privacy becomes more urgent. Although the body of work in privacy has been steadily growing over the past few years, research on the privacy…

Deep learning has achieved overwhelming success, spanning from discriminative models to generative models. In particular, deep generative models have facilitated a new level of performance in a myriad of areas, ranging from media…

Deep Neural Network (DNN) models have been shown to have high empirical privacy leakages. Clinical language models (CLMs) trained on clinical data have been used to improve performance in biomedical natural language processing tasks. In…

Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients of the models shared in training. Previous attacks…

Machine Learning (ML) models have been shown to potentially leak sensitive information, thus raising privacy concerns in ML-driven applications. This inspired recent research on removing the influence of specific data samples from a trained…

Private regression has received attention from both database and security communities. Recent work by Fredrikson et al. (USENIX Security 2014) analyzed the functional mechanism (Zhang et al. VLDB 2012) for training linear regression models…

Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during training. Instead, to mitigate privacy risks, we rely on generic…

Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data…

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…

Is overparameterization a privacy liability? In this work, we study the effect that the number of parameters has on a classifier's vulnerability to membership inference attacks. We first demonstrate how the number of parameters of a model…

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This article provides theoretical guarantees by exploring the…

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…

A key promise of machine learning is the ability to assist users with personal tasks. Because the personal context required to make accurate predictions is often sensitive, we require systems that protect privacy. A gold standard…