Farhad Farokhi

research

∙ 09/20/2023

Information Leakage from Data Updates in Machine Learning Models

In this paper we consider the setting where machine learning models are ...

0 Tian Hui, et al. ∙

research

∙ 09/18/2023

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...

0 Yuen-Man Pun, et al. ∙

research

∙ 07/24/2023

Maximal Quantum Information Leakage

A new measure of information leakage for quantum encoding of classical d...

0 Farhad Farokhi, et al. ∙

research

∙ 02/24/2023

Privacy Against Hypothesis-Testing Adversaries for Quantum Computing

A novel definition for data privacy in quantum computing based on quantu...

0 Farhad Farokhi, et al. ∙

research

∙ 02/15/2023

Distributionally-Robust Optimization with Noisy Data for Discrete Uncertainties Using Total Variation Distance

Stochastic programs where the uncertainty distribution must be inferred ...

0 Farhad Farokhi, et al. ∙

research

∙ 11/01/2021

Safe Learning of Linear Time-Invariant Systems

We consider safety in simultaneous learning and control of discrete-time...

0 Farhad Farokhi, et al. ∙

research

∙ 10/11/2021

Optimal Stochastic Evasive Maneuvers Using the Schrodinger's Equation

In this paper, preys with stochastic evasion policies are considered. Th...

0 Farhad Farokhi, et al. ∙

research

∙ 08/09/2021

Zero-Error Feedback Capacity of Finite-State Additive Noise Channels for Stabilization of Linear Systems

It is known that for a discrete channel with correlated additive noise, ...

0 Amir Saberi, et al. ∙

research

∙ 06/18/2021

Sharing in a Trustless World: Privacy-Preserving Data Analytics with Potentially Cheating Participants

Lack of trust between organisations and privacy concerns about their dat...

0 Tham Nguyen, et al. ∙

research

∙ 03/02/2021

Safe Learning of Uncertain Environments for Nonlinear Control-Affine Systems

In many learning based control methodologies, learning the unknown dynam...

0 Farhad Farokhi, et al. ∙

research

∙ 01/24/2021

A Linear Reduction Method for Local Differential Privacy and Log-lift

This paper considers the problem of publishing data X while protecting c...

0 Ni Ding, et al. ∙

research

∙ 01/18/2021

Optimal Pre-Processing to Achieve Fairness and Its Relationship with Total Variation Barycenter

We use disparate impact, i.e., the extent that the probability of observ...

0 Farhad Farokhi, et al. ∙

research

∙ 11/30/2020

Gradient Sparsification Can Improve Performance of Differentially-Private Convex Machine Learning

We use gradient sparsification to reduce the adverse effect of different...

0 Farhad Farokhi, et al. ∙

research

∙ 11/24/2020

When Machine Learning Meets Privacy: A Survey and Outlook

The newly emerged machine learning (e.g. deep learning) methods have bec...

69 Bo Liu, et al. ∙

research

∙ 10/20/2020

Non-Stochastic Private Function Evaluation

We consider private function evaluation to provide query responses based...

0 Farhad Farokhi, et al. ∙

research

∙ 08/28/2020

Deconvoluting Kernel Density Estimation and Regression for Locally Differentially Private Data

Local differential privacy has become the gold-standard of privacy liter...

5 Farhad Farokhi, et al. ∙

research

∙ 08/11/2020

Security Versus Privacy

Linear queries can be submitted to a server containing private data. The...

0 Farhad Farokhi, et al. ∙

research

∙ 06/24/2020

Distributionally-Robust Machine Learning Using Locally Differentially-Private Data

We consider machine learning, particularly regression, using locally-dif...

12 Farhad Farokhi, et al. ∙

research

∙ 06/02/2020

Online Stochastic Convex Optimization: Wasserstein Distance Variation

Distributionally-robust optimization is often studied for a fixed set of...

38 Iman Shames, et al. ∙

research

∙ 05/29/2020

An Explicit Formula for the Zero-Error Feedback Capacity of a Class of Finite-State Additive Noise Channels

It is known that for a discrete channel with correlated additive noise, ...

0 Amir Saberi, et al. ∙

research

∙ 04/23/2020

Measuring Information Leakage in Non-stochastic Brute-Force Guessing

We propose an operational measure of information leakage in a non-stocha...

0 Farhad Farokhi, et al. ∙

research

∙ 03/24/2020

Bounded state Estimation over Finite-State Channels: Relating Topological Entropy and Zero-Error Capacity

We investigate bounded state estimation of linear systems over finite-st...

0 Amir Saberi, et al. ∙

research

∙ 03/18/2020

Predicting Performance of Asynchronous Differentially-Private Learning

We consider training machine learning models using Training data located...

0 Farhad Farokhi, et al. ∙

research

∙ 02/17/2020

Data and Model Dependencies of Membership Inference Attack

Machine Learning (ML) techniques are used by most data-driven organisati...

0 Shakila Mahjabin Tonni, et al. ∙

research

∙ 01/29/2020

Regularization Helps with Mitigating Poisoning Attacks: Distributionally-Robust Machine Learning Using the Wasserstein Distance

We use distributionally-robust optimization for machine learning to miti...

0 Farhad Farokhi, et al. ∙

research

∙ 01/29/2020

Modelling and Quantifying Membership Information Leakage in Machine Learning

Machine learning models have been shown to be vulnerable to membership i...

4 Farhad Farokhi, et al. ∙

research

∙ 12/29/2019

Privacy-Preserving Public Release of Datasets for Support Vector Machine Classification

We consider the problem of publicly releasing a dataset for support vect...

43 Farhad Farokhi, et al. ∙

research

∙ 11/12/2019

Developing Non-Stochastic Privacy-Preserving Policies Using Agglomerative Clustering

We consider a non-stochastic privacy-preserving problem in which an adve...

0 Ni Ding, et al. ∙

research

∙ 10/29/2019

Noiseless Privacy

In this paper, we define noiseless privacy, as a non-stochastic rival to...

0 Farhad Farokhi, et al. ∙

research

∙ 10/05/2019

A Fundamental Bound on Performance of Non-Intrusive Load Monitoring with Application to Smart Meter Privacy

We prove that the expected estimation error of non-intrusive load monito...

0 Farhad Farokhi, et al. ∙

research

∙ 09/25/2019

Differential Privacy for Evolving Almost-Periodic Datasets with Continual Linear Queries: Application to Energy Data Privacy

For evolving datasets with continual reports, the composition rule for d...

0 Farhad Farokhi, et al. ∙

research

∙ 08/14/2019

Taking a Lesson from Quantum Particles for Statistical Data Privacy

Privacy is under threat from artificial intelligence revolution fueled b...

0 Farhad Farokhi, et al. ∙

research

∙ 08/12/2019

Discounted Differential Privacy: Privacy of Evolving Datasets over an Infinite Horizon

In this paper, we define discounted differential privacy, as an alternat...

0 Farhad Farokhi, et al. ∙

research

∙ 06/24/2019

A Game-Theoretic Approach to Adversarial Linear Support Vector Classification

In this paper, we employ a game-theoretic model to analyze the interacti...

0 Farhad Farokhi, et al. ∙

research

∙ 06/24/2019

The Value of Collaboration in Convex Machine Learning with Differential Privacy

In this paper, we apply machine learning to distributed private data own...

6 Nan Wu, et al. ∙

research

∙ 04/16/2019

Non-Stochastic Hypothesis Testing with Application to Privacy Against Hypothesis-Testing Adversary

In this paper, we consider privacy against hypothesis testing adversarie...

0 Farhad Farokhi, et al. ∙

research

∙ 02/19/2019

Implementing Homomorphic Encryption Based Secure Feedback Control for Physical Systems

This paper is about an encryption based approach to the secure implement...

0 Julian Tran, et al. ∙

research

∙ 02/02/2019

State Estimation over Worst-Case Erasure and Symmetric Channels with Memory

Worst-case models of erasure and symmetric channels are investigated, in...

0 Amir Saberi, et al. ∙

research

∙ 12/11/2018

Secure and Private Implementation of Dynamic Controllers Using Semi-Homomorphic Encryption

This paper presents a secure and private implementation of linear time-i...

0 Carlos Murguia, et al. ∙

research

∙ 10/26/2018

Development and Analysis of Deterministic Privacy-Preserving Policies Using Non-Stochastic Information Theory

A non-stochastic privacy metric using non-stochastic information theory ...

0 Farhad Farokhi, et al. ∙

research

∙ 08/28/2018

Ensuring Privacy with Constrained Additive Noise by Minimizing Fisher Information

The problem of preserving the privacy of individual entries of a databas...

0 Farhad Farokhi, et al. ∙

Farhad Farokhi

Featured Co-authors