arXiv research

Novel compression method preserves privacy while reducing communication costs.

Improves privacy amplification by shuffling for differential privacy.

Differential privacy has emerged as a gold standard in privacy-preserving data analysis. A popular variant is local differential privacy, where the data holder is the trusted curator. A major barrier, however, towards a wider adoption of this model is that it offers a poor privacy-utility tradeoff. In this work, we add…

New method recovers graph latent positions under edge differential privacy.

Paper tackles privacy-preserving data density issues using deconvolution.

Data processing inequalities link Fisher information to local differential privacy constraints.

This paper improves privacy accounting in decentralized FL using f-Differential Privacy.

LDP is equivalent to contraction of E_γ-divergence, impacting privacy and utility.

Noise-aware Bayesian inference framework for locally private data collection.

Paper tackles federated learning with privacy, enhancing target data analysis.

New bounds for LDP with heterogeneous privacy levels guaranteeing high probability of accuracy.

New federated $f$-differential privacy for collaborative learning.

Improved shuffling technique amplifies privacy guarantees for anonymous data contributions.

Sensitive statistics are often collected across sets of users, with repeated collection of reports done over time. For example, trends in users' private preferences or software usage may be monitored via such reports. We study the collection of such statistics in the local differential privacy (LDP) model, and describe…

New method estimates discrete distributions while protecting privacy.

The paper studies MAB problems with LDP to balance privacy and service quality.

We study $E_γ$-divergence contraction and its privacy implications.

Paper addresses privacy and robustness in stochastic linear bandits.

Paper proposes a federated learning method for quantile inference with local differential privacy.

This paper benchmarks privacy-preserving machine learning on medical images.

Interactive privacy mechanisms improve spectral density estimation under local differential privacy.

The paper proposes a fair and private decentralized deep learning framework.

New methods test discrete distributions faster with local privacy constraints.

FedSel uses local differential privacy to protect data privacy in federated SGD.

Paper improves privacy-accuracy balance in federated learning.

Paper optimizes privacy-preserving distribution estimation for sparse data.

Paper addresses privacy in combinatorial semi-bandits with improved bounds.

New methods protect privacy while providing accurate prediction sets.

FLAME improves privacy in federated learning without trusted parties.

This work studies differential privacy in the context of the recently proposed shuffle model. Unlike in the local model, where the server collecting privatized data from users can track back an input to a specific user, in the shuffle model users submit their privatized inputs to a server anonymously. This setup yields…

Conformal-DP improves differential privacy on manifold data by calibrating perturbations based on local densities.

This paper analyzes user-level local differential privacy in distributed systems.

Framework for robust decision making in changing environments with privacy constraints.

A privacy-preserving algorithm for high-dimensional bandits.

The paper addresses privacy-preserving BAI in clinical trials and user studies.

Develops new instance-optimality concepts in differential privacy.

LDP-Fed protects privacy in federated learning with neural networks.

In machine learning, classification models need to be trained in order to predict class labels. When the training data contains personal information about individuals, collecting training data becomes difficult due to privacy concerns. Local differential privacy is a definition to measure the individual privacy when th…

A new algorithm estimates mean under varying user data sizes with local differential privacy.

In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection. Concomitant with this rise in decentralized data are increasing challenges of maintaining privacy while allowing enough in…

We consider the binary classification problem in a setup that preserves the privacy of the original sample. We provide a privacy mechanism that is locally differentially private and then construct a classifier based on the private sample that is universally consistent in Euclidean spaces. Under stronger assumptions, we…

New framework provides privacy guarantees for practical federated learning.

New approach preserves privacy in high-dimensional data using representation learning.

Local differential privacy (LDP) is a strong notion of privacy for individual users that often comes at the expense of a significant drop in utility. The classical definition of LDP assumes that all elements in the data domain are equally sensitive. However, in many applications, some symbols are more sensitive than ot…

New findings show privacy affects generalization error in a non-monotonic way.

Traditionally, there are two models on differential privacy: the central model and the local model. The central model focuses on the machine learning model and the local model focuses on the training data. In this paper, we study the \textit{input perturbation} method in differentially private empirical risk minimizati…

BCDP enhances privacy by protecting sensitive features more precisely.

Study local differential privacy methods for estimating power sums of discrete distributions.