相关论文: Label Differential Privacy via Aggregation

Differential privacy (DP) allows the quantification of privacy loss when the data of individuals is subjected to algorithmic processing such as machine learning, as well as the provision of objective privacy guarantees. However, while…

Differentially private (DP) mechanisms face the challenge of providing accurate results while protecting their inputs: the privacy-utility trade-off. A simple but powerful technique for DP adds noise to sensitivity-bounded query outputs to…

We consider training models on private data that are distributed across user devices. To ensure privacy, we add on-device noise and use secure aggregation so that only the noisy sum is revealed to the server. We present a comprehensive…

In spite that Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively, recent studies have pointed out that the naive FL is susceptible to gradient…

In this paper, we introduce BlockRR, a novel and unified randomized-response mechanism for label differential privacy. This framework generalizes existed RR-type mechanisms as special cases under specific parameter settings, which…

Federated machine learning leverages edge computing to develop models from network user data, but privacy in federated learning remains a major challenge. Techniques using differential privacy have been proposed to address this, but bring…

Federated learning (FL) with differential privacy (DP) provides a framework for collaborative machine learning, enabling clients to train a shared model while adhering to strict privacy constraints. The framework allows each client to have…

Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving client's private data from being shared among different parties. Nevertheless, private information can still be divulged by analyzing…

We study the Densest Subgraph (DSG) problem under the additional constraint of differential privacy. DSG is a fundamental theoretical question which plays a central role in graph analytics, and so privacy is a natural requirement. All known…

Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to limit the risk of information leakage. The scale of the…

Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing approaches to handling noisy labels fall into two…

We study person-level differentially private (DP) mean estimation in the case where each person holds multiple samples. DP here requires the usual notion of distributional stability when $\textit{all}$ of a person's datapoints can be…

Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. Only processed or `smashed' data can be transmitted from the clients to the server during the SL…

Aggregating statistics over geographical regions is important for many applications, such as analyzing income, election results, and disease spread. However, the sensitive nature of this data necessitates strong privacy protections to…

Non-interactive Local Differential Privacy (LDP) requires data analysts to collect data from users through noisy channel at once. In this paper, we extend the frontiers of Non-interactive LDP learning and estimation from several aspects.…

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…

Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they…

This paper establishes the equivalence between Local Differential Privacy (LDP) and a global limit on learning any knowledge specific to a queried object. However, an output from an LDP query is not necessarily required to provide exact…

Federated learning is a distributed learning setting where the main aim is to train machine learning models without having to share raw data but only what is required for learning. To guarantee training data privacy and high-utility models,…

Traditional differential privacy is independent of the data distribution. However, this is not well-matched with the modern machine learning context, where models are trained on specific data. As a result, achieving meaningful privacy…