Related papers: On Local Mutual-Information Privacy
Machine learning (ML) algorithms rely primarily on the availability of training data, and, depending on the domain, these data may include sensitive information about the data providers, thus leading to significant privacy issues.…
We investigate the local differential privacy (LDP) guarantees of a randomized privacy mechanism via its contraction properties. We first show that LDP constraints can be equivalently cast in terms of the contraction coefficient of the…
In modern distributed computing applications, such as federated learning and AIoT systems, protecting privacy is crucial to prevent adversarial parties from colluding to steal others' private information. However, guaranteeing the utility…
Differential privacy (DP) is typically formulated as a worst-case privacy guarantee over all individuals in a database. More recently, extensions to individual subjects or their attributes, have been introduced. Under the…
Reinforcement learning algorithms are widely used in domains where it is desirable to provide a personalized service. In these domains it is common that user data contains sensitive information that needs to be protected from third parties.…
This paper investigates lift, the likelihood ratio between the posterior and prior belief about sensitive features in a dataset. Maximum and minimum lifts over sensitive features quantify the adversary's knowledge gain and should be bounded…
Differential privacy protects an individual's privacy by perturbing data on an aggregated level (DP) or individual level (LDP). We report four online human-subject experiments investigating the effects of using different approaches to…
Based on binary inquiries, we developed an algorithm to estimate population quantiles under Local Differential Privacy (LDP). By self-normalizing, our algorithm provides asymptotically normal estimation with valid inference, resulting in…
Neural networks are susceptible to privacy attacks that can extract private information of the training set. To cope, several training algorithms guarantee differential privacy (DP) by adding noise to their computation. However, DP requires…
Local differential privacy (LDP) has been deemed as the de facto measure for privacy-preserving distributed data collection and analysis. Recently, researchers have extended LDP to the basic data type in NoSQL systems: the key-value data,…
We study privacy guarantees in the framework of pointwise maximal leakage (PML) that satisfy two requirements: they are robust under post-processing and upper bound the failure probability, i.e., the probability that the information leakage…
The problem of estimating a parameter in the drift coefficient is addressed for $N$ discretely observed independent and identically distributed stochastic differential equations (SDEs). This is done considering additional constraints,…
We study locally differentially private algorithms for reinforcement learning to obtain a robust policy that performs well across distributed private environments. Our algorithm protects the information of local agents' models from being…
Consider statistical learning (e.g. discrete distribution estimation) with local $\epsilon$-differential privacy, which preserves each data provider's privacy locally, we aim to optimize statistical data utility under the privacy…
Label differential privacy (DP) is designed for learning problems involving private labels and public features. While various methods have been proposed for learning under label DP, the theoretical limits remain largely unexplored. In this…
The private collection of multiple statistics from a population is a fundamental statistical problem. One possible approach to realize this is to rely on the local model of differential privacy (LDP). Numerous LDP protocols have been…
We consider data release protocols for data $X=(S,U)$, where $S$ is sensitive; the released data $Y$ contains as much information about $X$ as possible, measured as $\operatorname{I}(X;Y)$, without leaking too much about $S$. We introduce…
Differential privacy (DP) considers a scenario, where an adversary has almost complete information about the entries of a database This worst-case assumption is likely to overestimate the privacy thread for an individual in real life.…
Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data…
We optimize the trade-off between privacy and utility in the high-privacy regime. We adopt local differential privacy (LDP) and its quantum extension, quantum local differential privacy (QLDP), for privacy protection, and investigate…