Search Results for author:
Found 22 papers, 1 papers with code
Optimal Universal Quantum Encoding for Statistical Inference
The optimal universal encoding strategy, i. e., the encoding strategy that maximizes the maximal quantum leakage, is proved to be attained by pure states.
Information Leakage from Data Updates in Machine Learning Models
We validate that two snapshots of the model can result in higher information leakage in comparison to having access to only the updated model.
Distributionally Time-Varying Online Stochastic Optimization under Polyak-Łojasiewicz Condition with Application in Conditional Value-at-Risk Statistical Learning
In this work, we consider a sequence of stochastic optimization problems following a time-varying distribution via the lens of online optimization.
Learning Safety Filters for Unknown Discrete-Time Linear Systems
A learning-based safety filter is developed for discrete-time linear time-invariant systems with unknown models subject to Gaussian noises with unknown covariance.
Toward nonlinear dynamic control over encrypted data for infinite time horizon
In this note, we demonstrate that it is possible to run a dynamic controller over encrypted data for an infinite time horizon if the output of the controller can be represented as a function of a fixed number of previous inputs and outputs.
Safe Learning of Uncertain Environments
We show that with an arbitrarily large probability we can guarantee that the state will remain in the safe set, while learning and control are carried out simultaneously, provided that a feasible solution exists for the optimization problem.
Optimal Pre-Processing to Achieve Fairness and Its Relationship with Total Variation Barycenter
Hence, the problem of finding the optimal pre-processing regiment for enforcing fairness can be cast as minimizing total variations distance between the distribution of the data before and after pre-processing subject to a constraint on the total variation distance between the distribution of the inputs given protected attributes.
Gradient Sparsification Can Improve Performance of Differentially-Private Convex Machine Learning
We prove that, for small privacy budgets, compression can improve performance of privacy-preserving machine learning models.
When Machine Learning Meets Privacy: A Survey and Outlook
The newly emerged machine learning (e. g. deep learning) methods have become a strong driving force to revolutionize a wide range of industries, such as smart healthcare, financial technology, and surveillance systems.
Deconvoluting Kernel Density Estimation and Regression for Locally Differentially Private Data
However, locally differential data can twist the probability density of the data because of the additive noise used to ensure privacy.
Distributionally-Robust Machine Learning Using Locally Differentially-Private Data
For general distributions, the distributionally-robust optimization problem can relaxed as a regularized machine learning problem with the Lipschitz constant of the machine learning model as a regularizer.
Online Stochastic Convex Optimization: Wasserstein Distance Variation
Distributionally-robust optimization is often studied for a fixed set of distributions rather than time-varying distributions that can drift significantly over time (which is, for instance, the case in finance and sociology due to underlying expansion of economy and evolution of demographics).
Bounded State Estimation over Finite-State Channels: Relating Topological Entropy and Zero-Error Capacity
We investigate state estimation of linear systems over channels having a finite state not known by the transmitter or receiver.
The Cost of Privacy in Asynchronous Differentially-Private Machine Learning
The experiments illustrate that collaboration among more than 10 data owners with at least 10, 000 records with privacy budgets greater than or equal to 1 results in a superior machine-learning model in comparison to a model trained in isolation on only one of the datasets, illustrating the value of collaboration and the cost of the privacy.
Data and Model Dependencies of Membership Inference Attack
Our results reveal the relationship between MIA accuracy and properties of the dataset and training model in use.
Uniformly Bounded State Estimation over Multiple Access Channels
This paper addresses the problem of distributed state estimation via multiple access channels (MACs).
Regularization Helps with Mitigating Poisoning Attacks: Distributionally-Robust Machine Learning Using the Wasserstein Distance
We provide performance guarantees for the trained model on the original data (not including the poison records) by training the model for the worst-case distribution on a neighbourhood around the empirical distribution (extracted from the training dataset corrupted by a poisoning attack) defined using the Wasserstein distance.
Modelling and Quantifying Membership Information Leakage in Machine Learning
We use conditional mutual information leakage to measure the amount of information leakage from the trained machine learning model about the presence of an individual in the training dataset.
Privacy-Preserving Public Release of Datasets for Support Vector Machine Classification
The optimal noise distribution is determined by maximizing a weighted sum of the measures of privacy and utility.
A Game-Theoretic Approach to Adversarial Linear Support Vector Classification
This results in computing a linear support vector machine classifier that is robust against adversarial input manipulations.
The Value of Collaboration in Convex Machine Learning with Differential Privacy
In this paper, we apply machine learning to distributed private data owned by multiple data owners, entities with access to non-overlapping training datasets.
