Farhad Farokhi

Using rényi-divergence and arimoto-rényi information to quantify membership information leakage

F Farokhi

Conference Proceedings  |  2021  |  2021 55th Annual Conference on Information Sciences and Systems, CISS 2021

Membership inference attacks, i.e., adversarial attacks inferring whether a data record is used for training a machine learning mo..

When Machine Learning Meets Privacy

Bo Liu, Ming Ding, Sina Shaham, Wenny Rahayu, Farhad Farokhi, Zihuai Lin

Journal article  |  2021  |  ACM Computing Surveys

The newly emerged machine learning (e.g., deep learning) methods have become a strong driving force to revolutionize a wide range ..

Feedback control using a strategic sensor

Farhad Farokhi

Journal article  |  2021  |  International Journal of Control

A dynamic estimation and control problem with a strategic sensor is considered. The strategic sensor may provide corrupted message..

The Cost of Privacy in Asynchronous Differentially-Private Machine Learning

Farhad Farokhi, Nan Wu, David Smith, Mohamed Ali Kaafar

Journal article  |  2021  |  IEEE Transactions on Information Forensics and Security

We consider training machine learning models using data located on multiple private and geographically-scattered servers with diff..

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

Ni Ding, Yucheng Liu, Farhad Farokhi

Conference Proceedings  |  2021  |  Proceeding of IEEE International Symposium on Information Theory

On Privacy of Dynamical Systems: An Optimal Probabilistic Mapping Approach

Carlos Murguia, Iman Shames, Farhad Farokhi, Dragan Nesic, H Vincent Poor

Journal article  |  2021  |  IEEE Transactions on Information Forensics and Security

We address the problem of maximizing privacy of stochastic dynamical systems whose state information is released through quantized..

Why Does Regularization Help with Mitigating Poisoning Attacks?

Farhad Farokhi

Journal article  |  2021  |  Neural Processing Letters

We use distributionally-robust optimization for machine learning to mitigate the effect of data poisoning attacks. We provide perf..

Deconvoluting kernel density estimation and regression for locally differentially private data.

Farhad Farokhi

Journal article  |  2020  |  Scientific Reports

Local differential privacy has become the gold-standard of privacy literature for gathering or releasing sensitive individual data..

Non-stochastic hypothesis testing for privacy

Farhad Farokhi

Journal article  |  2020  |  IET Information Security

In this paper, we consider privacy against hypothesis testing adversaries within a non-stochastic framework. We develop a theory o..

Review of results on smart-meter privacy by data manipulation, demand shaping, and load scheduling

F Farokhi

Journal article  |  2020  |  IET Smart Grid

Simple analysis of energy consumption patterns recorded by smart meters can be used to deduce household occupancy. With access to ..