Related papers: Differentially Private Bayesian Programming
Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…
Differential privacy is a cryptographically-motivated approach to privacy that has become a very active field of research over the last decade in theoretical computer science and machine learning. In this paradigm one assumes there is a…
In this work, we investigate binary classification under the constraints of both differential privacy and fairness. We first propose an algorithm based on the decoupling technique for learning a classifier with only fairness guarantee. This…
Differential privacy is becoming a gold standard for privacy research; it offers a guaranteed bound on loss of privacy due to release of query results, even under worst-case assumptions. The theory of differential privacy is an active…
Differential privacy provides a strong form of privacy and allows preserving most of the original characteristics of the dataset. Utilizing these benefits requires one to design specific differentially private data analysis algorithms. In…
When releasing outputs from confidential data, agencies need to balance the analytical usefulness of the released data with the obligation to protect data subjects' confidentiality. For releases satisfying differential privacy, this balance…
The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…
This paper proposes new methodologies for conducting practical differentially private (DP) estimation and inference in high-dimensional linear regression. We first introduce a DP Bayesian Information Criterion (DP-BIC) for selecting the…
Differentially private machine learning trains models while protecting privacy of the sensitive training data. The key to obtain differentially private models is to introduce noise/randomness to the training process. In particular, existing…
Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a dataset or even…
The adoption of differential privacy is growing but the complexity of designing private, efficient and accurate algorithms is still high. We propose a novel programming framework and system, Ektelo, for implementing both existing and new…
Differential privacy mechanisms such as the Gaussian or Laplace mechanism have been widely used in data analytics for preserving individual privacy. However, they are mostly designed for continuous outputs and are unsuitable for scenarios…
Large language models (LLMs) have presented outstanding performance in code generation and completion. However, fine-tuning these models on private datasets can raise privacy and proprietary concerns, such as the leakage of sensitive…
A distinguishing characteristic of federated learning is that the (local) client data could have statistical heterogeneity. This heterogeneity has motivated the design of personalized learning, where individual (personalized) models are…
In recent years, federated learning (FL) has emerged as a prominent paradigm in distributed machine learning. Despite the partial safeguarding of agents' information within FL systems, a malicious adversary can potentially infer sensitive…
Large data collections required for the training of neural networks often contain sensitive information such as the medical histories of patients, and the privacy of the training data must be preserved. In this paper, we introduce a dropout…
When analysing Differentially Private (DP) machine learning pipelines, the potential privacy cost of data-dependent pre-processing is frequently overlooked in privacy accounting. In this work, we propose a general framework to evaluate the…
Information disclosure can compromise privacy when revealed information is correlated with private information. We consider the notion of inferential privacy, which measures privacy leakage by bounding the inferential power a Bayesian…
So far, privacy models follow two paradigms. The first paradigm, termed inferential privacy in this paper, focuses on the risk due to statistical inference of sensitive information about a target record from other records in the database.…
We propose the approach of model-based differentially private synthesis (modips) in the Bayesian framework for releasing individual-level surrogate/synthetic datasets with privacy guarantees given the original data. The modips technique…