activity
20192021
most citedWhen Machine Learning Meets Privacy: A Survey and Outlook

97 citations · 111 across the 15 of their papers we have counts for

collaborators

27 papers

cs.IT2021

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…

cs.CR2021

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…

cs.LG2021

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…

cs.IT2021

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…

cs.IT2021

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…

math.OC20202 cited

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…