相关论文: Enabling Trade-offs in Privacy and Utility in Geno…

We study how inherent randomness in the training process -- where each sample (or client in federated learning) contributes only to a randomly selected portion of training -- can be leveraged for privacy amplification. This includes (1)…

Differential privacy has become a widely accepted notion of privacy, leading to the introduction and deployment of numerous privatization mechanisms. However, ensuring the privacy guarantee is an error-prone process, both in designing…

We study a classical problem in private prediction, the problem of computing an $(m\epsilon, \delta)$-differentially private majority of $K$ $(\epsilon, \Delta)$-differentially private algorithms for $1 \leq m \leq K$ and $1 > \delta \geq…

In this paper, we present an optimization-based formulation for privacy-utility tradeoff in the Ensemble and Unscented Kalman filtering framework, with a focus on space situational awareness. Privacy and utility are defined in terms of a…

In settings like vaccination registries, individuals act after observing others, and the resulting public records can expose private information. We study privacy-preserving sequential learning, where agents add endogenous noise to their…

How to achieve the tradeoff between privacy and utility is one of fundamental problems in private data analysis.In this paper, we give a rigourous differential privacy analysis of networks in the appearance of covariates via a generalized…

Text-to-image diffusion models have demonstrated remarkable capabilities in creating images highly aligned with user prompts, yet their proclivity for memorizing training set images has sparked concerns about the originality of the…

Genetic association studies are becoming an important component of medical research. To cite one instance, pharmacogenomics which is gaining prominence as a useful tool for personalized medicine is heavily reliant on results from genetic…

The digital era has raised many societal challenges, including ICT's rising energy consumption and protecting privacy of personal data processing. This paper considers both aspects in relation to machine learning accuracy in an…

A Private Repetition algorithm takes as input a differentially private algorithm with constant success probability and boosts it to one that succeeds with high probability. These algorithms are closely related to private metaselection…

Rapid advances in human genomics are enabling researchers to gain a better understanding of the role of the genome in our health and well-being, stimulating hope for more effective and cost efficient healthcare. However, this also prompts a…

For scalable machine learning on large data sets, subsampling a representative subset is a common approach for efficient model training. This is often achieved through importance sampling, whereby informative data points are sampled more…

We explore the trade-off between privacy and statistical utility in private two-sample testing under local differential privacy (LDP) for both multinomial and continuous data. We begin by addressing the multinomial case, where we introduce…

Historically, machine learning methods have not been designed with security in mind. In turn, this has given rise to adversarial examples, carefully perturbed input samples aimed to mislead detection at test time, which have been applied to…

This paper investigates the issue of privacy in a learning scenario where users share knowledge for a recommendation task. Our study contributes to the growing body of research on privacy-preserving machine learning and underscores the need…

Data sharing between different organizations is an essential process in today's connected world. However, recently there were many concerns about data sharing as sharing sensitive information can jeopardize users' privacy. To preserve the…

Large language models (LLMs) and AI agents are increasingly integrated into enterprise systems to access internal databases and generate context-aware responses. While such integration improves productivity and decision support, the model…

DNA sequencing is becoming increasingly commonplace, both in medical and direct-to-consumer settings. To promote discovery, collected genomic data is often de-identified and shared, either in public repositories, such as OpenSNP, or with…

In this work, we focus on protection against identity disclosure in the publication of sparse multidimensional data. Existing multidimensional anonymization techniquesa) protect the privacy of users either by altering the set of…

With the rapid advancement of deep learning technology, pre-trained encoder models have demonstrated exceptional feature extraction capabilities, playing a pivotal role in the research and application of deep learning. However, their…