97 citations · 163 across the 34 of their papers we have counts for
36 papers
Privacy-Preserving State Estimation with Crowd Sensors: An Information-Theoretic Respective
Farhad Farokhi
Privacy-preserving state estimation for linear time-invariant dynamical systems with crowd sensors is considered. At any time step, the estimator has access to measurements from a…
Maximal Information Leakage from Quantum Encoding of Classical Data
Farhad Farokhi
A new measure of information leakage for quantum encoding of classical data is defined. An adversary can access a single copy of the state of a quantum system that encodes some cla…
Privacy Against Hypothesis-Testing Adversaries for Quantum Computing
Farhad Farokhi
A novel definition for data privacy in quantum computing based on quantum hypothesis testing is presented in this paper. The parameters in this privacy notion possess an operationa…
Distributionally-Robust Optimization with Noisy Data for Discrete Uncertainties Using Total Variation Distance
Farhad Farokhi
Stochastic programs where the uncertainty distribution must be inferred from noisy data samples are considered. The stochastic programs are approximated with distributionally-robus…
Zero-Error Feedback Capacity for Bounded Stabilization and Finite-State Additive Noise Channels
Amir Saberi, Farhad Farokhi, Girish Nair
This article studies the zero-error feedback capacity of {\em causal} discrete channels with memory. First, by extending the classical zero-error feedback capacity concept, a new n…
Measuring Information Leakage in Non-stochastic Brute-Force Guessing
Ni Ding, Farhad Farokhi
This paper proposes an operational measure of non-stochastic information leakage to formalize privacy against a brute-force guessing adversary. The information is measured by non-p…
Sharing in a Trustless World: Privacy-Preserving Data Analytics with Potentially Cheating Participants
Tham Nguyen, Hassan Jameel Asghar, Raghav Bhakar +2
Lack of trust between organisations and privacy concerns about their data are impediments to an otherwise potentially symbiotic joint data analysis. We propose DataRing, a data sha…
Safe Learning of Uncertain Environments
Farhad Farokhi, Alex Leong, Iman Shames +1
In many learning based control methodologies, learning the unknown dynamic model precedes the control phase, while the aim is to control the system such that it remains in some saf…
A Linear Reduction Method for Local Differential Privacy and Log-lift
Ni Ding, Yucheng Liu, Farhad Farokhi
This paper considers the problem of publishing data while protecting correlated sensitive information . We propose a linear method to generate the sanitized data with th…
Optimal Pre-Processing to Achieve Fairness and Its Relationship with Total Variation Barycenter
Farhad Farokhi
We use disparate impact, i.e., the extent that the probability of observing an output depends on protected attributes such as race and gender, to measure fairness. We prove that di…
Rigid-profile input scheduling under constrained dynamics with a water network application
Adair Lang, Michael Cantoni, Farhad Farokhi +1
The motivation for this work stems from the problem of scheduling requests for flow at supply points along an automated network of open-water channels. The off-take flows are rigid…
Gradient Sparsification Can Improve Performance of Differentially-Private Convex Machine Learning
Farhad Farokhi
We use gradient sparsification to reduce the adverse effect of differential privacy noise on performance of private machine learning models. To this aim, we employ compressed sensi…
When Machine Learning Meets Privacy: A Survey and Outlook
Bo Liu, Ming Ding, Sina Shaham +3
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…
Non-Stochastic Private Function Evaluation
Farhad Farokhi, Girish Nair
We consider private function evaluation to provide query responses based on private data of multiple untrusted entities in such a way that each cannot learn something substantially…
Structured preconditioning of conjugate gradients for path-graph network optimal control problems
Armaghan Zafar, Michael Cantoni, Farhad Farokhi
A structured preconditioned conjugate gradient (PCG) solver is developed for the Newton steps in second-order methods for a class of constrained network optimal control problems. O…
Deconvoluting Kernel Density Estimation and Regression for Locally Differentially Private Data
Farhad Farokhi
Local differential privacy has become the gold-standard of privacy literature for gathering or releasing sensitive individual data points in a privacy-preserving manner. However, l…
Distributionally-Robust Machine Learning Using Locally Differentially-Private Data
Farhad Farokhi
We consider machine learning, particularly regression, using locally-differentially private datasets. The Wasserstein distance is used to define an ambiguity set centered at the em…
Online Stochastic Convex Optimization: Wasserstein Distance Variation
Iman Shames, Farhad Farokhi
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…
An Explicit Formula for the Zero-Error Feedback Capacity of a Class of Finite-State Additive Noise Channels
Amir Saberi, Farhad Farokhi, Girish N. Nair
It is known that for a discrete channel with correlated additive noise, the ordinary capacity with or without feedback both equal , where $ \mathcal{H}(Z)…
Measuring Information Leakage in Non-stochastic Brute-Force Guessing
Farhad Farokhi, Ni Ding
We propose an operational measure of information leakage in a non-stochastic setting to formalize privacy against a brute-force guessing adversary. We use uncertain variables, non-…
Bounded State Estimation over Finite-State Channels: Relating Topological Entropy and Zero-Error Capacity
Amir Saberi, Farhad Farokhi, Girish N. Nair
We investigate state estimation of linear systems over channels having a finite state not known by the transmitter or receiver. We show that similar to memoryless channels, zero-er…
The Cost of Privacy in Asynchronous Differentially-Private Machine Learning
Farhad Farokhi, Nan Wu, David Smith +1
We consider training machine learning models using Training data located on multiple private and geographically-scattered servers with different privacy settings. Due to the distri…
Data and Model Dependencies of Membership Inference Attack
Shakila Mahjabin Tonni, Dinusha Vatsalan, Farhad Farokhi +3
Machine learning (ML) models have been shown to be vulnerable to Membership Inference Attacks (MIA), which infer the membership of a given data point in the target dataset by obser…
Regularization Helps with Mitigating Poisoning Attacks: Distributionally-Robust Machine Learning Using the Wasserstein Distance
Farhad Farokhi
We use distributionally-robust optimization for machine learning to mitigate the effect of data poisoning attacks. We provide performance guarantees for the trained model on the or…