Related papers: Epsilon*: Privacy Metric for Machine Learning Mode…
Machine unlearning, an emerging research topic focusing on compliance with data privacy regulations, enables trained models to remove the information learned from specific data. While many existing methods indirectly address this issue by…
As in traditional machine learning models, models trained with federated learning may exhibit disparate performance across demographic groups. Model holders must identify these disparities to mitigate undue harm to the groups. However,…
The integration of machine learning (ML) in numerous critical applications introduces a range of privacy concerns for individuals who provide their datasets for model training. One such privacy risk is Membership Inference (MI), in which an…
Generative models producing synthetic data are meant to provide a privacy-friendly approach to releasing data. However, their privacy guarantees are only considered robust when models satisfy Differential Privacy (DP). Alas, this is not a…
Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum. Yet, in reality, these models are part of larger systems that include components for training data filtering, output monitoring,…
Artificial intelligence systems are prevalent in everyday life, with use cases in retail, manufacturing, health, and many other fields. With the rise in AI adoption, associated risks have been identified, including privacy risks to the…
Designing privacy-preserving machine learning algorithms has received great attention in recent years, especially in the setting when the data contains sensitive information. Differential privacy (DP) is a widely used mechanism for data…
Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving…
Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…
In statistical disclosure control, the goal of data analysis is twofold: The released information must provide accurate and useful statistics about the underlying population of interest, while minimizing the potential for an individual…
In this note, we consider the problem of differentially privately (DP) computing an anonymized histogram, which is defined as the multiset of counts of the input dataset (without bucket labels). In the low-privacy regime $\epsilon \geq 1$,…
Model Inversion attacks aim to reconstruct information from private training data by exploiting access to a target model. Nearly all recent MI studies evaluate attack success using a standard framework that computes attack accuracy through…
While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference, where an adversary…
This paper introduces a paradigm shift in the way privacy is defined, driven by a novel interpretation of the fundamental result of Dwork and Naor about the impossibility of absolute disclosure prevention. We propose a general model of…
We consider the problem of fitting a linear model to data held by individuals who are concerned about their privacy. Incentivizing most players to truthfully report their data to the analyst constrains our design to mechanisms that provide…
This work proposes an algorithmic method to verify differential privacy for estimation mechanisms with performance guarantees. Differential privacy makes it hard to distinguish outputs of a mechanism produced by adjacent inputs. While…
Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such…
The worldwide adoption of machine learning (ML) and deep learning models, particularly in critical sectors, such as healthcare and finance, presents substantial challenges in maintaining individual privacy and fairness. These two elements…
Label differential privacy (label-DP) is a popular framework for training private ML models on datasets with public features and sensitive private labels. Despite its rigorous privacy guarantee, it has been observed that in practice…
Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only…