Related papers: Higher-Order Approximate Relational Refinement Typ…

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

\epsilon-differential privacy is the state-of-the-art model for releasing sensitive information while protecting privacy. Numerous methods have been proposed to enforce epsilon-differential privacy in various analytical tasks, e.g.,…

When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors. We propose to use the learning-augmented algorithms (or algorithms…

Computing accurate low rank approximations of large matrices is a fundamental data mining task. In many applications however the matrix contains sensitive information about individuals. In such case we would like to release a low rank…

Differentially-private histograms have emerged as a key tool for location privacy. While past mechanisms have included theoretical & experimental analysis, it has recently been observed that much of the existing literature does not fully…

Machine learning (ML) classifiers are invaluable building blocks that have been used in many fields. High quality training dataset collected from multiple data providers is essential to train accurate classifiers. However, it raises concern…

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…

In this paper, we present a comprehensive framework for differential privacy over affine manifolds and validate its usefulness in the contexts of differentially private cloud-based control and average consensus. We consider differential…

Differential privacy is a popular privacy-enhancing technology that has been deployed both in industry and government agencies. Unfortunately, existing explanations of differential privacy fail to set accurate privacy expectations for data…

Curators of sensitive datasets sometimes need to know whether queries against the data are differentially private [Dwork et al. 2006]. Two sorts of logics have been proposed for checking this property: (1) type systems and other static…

Language models are widely deployed to provide automatic text completion services in user products. However, recent research has revealed that language models (especially large ones) bear considerable risk of memorizing private training…

Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use…

Differential Privacy (DP) provides an elegant mathematical framework for defining a provable disclosure risk in the presence of arbitrary adversaries; it guarantees that whether an individual is in a database or not, the results of a DP…

Nowadays, machine learning models and applications have become increasingly pervasive. With this rapid increase in the development and employment of machine learning models, a concern regarding privacy has risen. Thus, there is a legitimate…

This work examines a novel question: how much randomness is needed to achieve local differential privacy (LDP)? A motivating scenario is providing {\em multiple levels of privacy} to multiple analysts, either for distribution or for…

Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data. This paper focuses on a class of regularized empirical risk minimization (ERM) machine learning problems, and develops…

Fine-tuning adapts a pretrained machine learning model to a small, sensitive dataset, but this process risks memorizing individual new data points, making the model vulnerable to adversaries who seek to extract sensitive information. In…

Differential privacy is a statistical definition of privacy that has attracted the interest of both academia and industry. Its formulations are easy to understand, but the differential privacy of databases is complicated to determine. One…

Aligning AI systems with human preferences typically suffers from the infamous reward hacking problem, where optimization of an imperfect reward model leads to undesired behaviors. In this paper, we investigate reward hacking in offline…

Relational properties describe multiple runs of one or more programs. They characterize many useful notions of security, program refinement, and equivalence for programs with diverse computational effects, and they have received much…