Related papers: Bounding Information Leakage in Machine Learning
Deep neural networks have been shown to be vulnerable to membership inference attacks wherein the attacker aims to detect whether specific input data were used to train the model. These attacks can potentially leak private or proprietary…
Privacy attacks on Machine Learning (ML) models often focus on inferring the existence of particular data points in the training data. However, what the adversary really wants to know is if a particular individual's (subject's) data was…
Generative models have demonstrated revolutionary success in various visual creation tasks, but in the meantime, they have been exposed to the threat of leaking private information of their training data. Several membership inference…
Federated Contrastive Learning (FCL) represents a burgeoning approach for learning from decentralized unlabeled data while upholding data privacy. In FCL, participant clients collaborate in learning a global encoder using unlabeled data,…
Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…
Federated learning is an established method for training machine learning models without sharing training data. However, recent work has shown that it cannot guarantee data privacy as shared gradients can still leak sensitive information.…
Generative models are increasingly used to produce privacy-preserving synthetic data as a safe alternative to sharing sensitive training datasets. However, we demonstrate that such synthetic releases can still leak information about the…
Artificial intelligence, machine learning, and deep learning as a service have become the status quo for many industries, leading to the widespread deployment of models that handle sensitive data. Well-performing models, the industry seeks,…
The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…
A number of recent works have demonstrated that API access to machine learning models leaks information about the dataset records used to train the models. Further, the work of \cite{somesh-overfit} shows that such membership inference…
In this work, the probability of an event under some joint distribution is bounded by measuring it with the product of the marginals instead (which is typically easier to analyze) together with a measure of the dependence between the two…
Inference attacks against Machine Learning (ML) models allow adversaries to learn sensitive information about training data, model parameters, etc. While researchers have studied, in depth, several kinds of attacks, they have done so in…
While machine learning (ML) has made tremendous progress during the past decade, recent research has shown that ML models are vulnerable to various security and privacy attacks. So far, most of the attacks in this field focus on…
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 dataset. These attacks are currently evaluated using…
The expanding integration of Large Language Models (LLMs) into recommender systems poses critical challenges to evaluation reliability. This paper identifies and investigates a previously overlooked issue: benchmark data leakage in…
Membership inference attacks (MIAs) pose a critical threat to the privacy of training data in deep learning. Despite significant progress in attack methodologies, our understanding of when and how models encode membership information during…
Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerable to privacy attacks. In this work, we further reveal this…
Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis. These applications are trained on datasets from many FL…
Membership inference (MI) determines if a sample was part of a victim model training set. Recent development of MI attacks focus on record-level membership inference which limits their application in many real-world scenarios. For example,…
Models can expose sensitive information about their training data. In an attribute inference attack, an adversary has partial knowledge of some training records and access to a model trained on those records, and infers the unknown values…