97 citations · 163 across the 34 of their papers we have counts for
8 papers · 1 filter
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…
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…
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…
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…
Modelling and Quantifying Membership Information Leakage in Machine Learning
Farhad Farokhi, Mohamed Ali Kaafar
Machine learning models have been shown to be vulnerable to membership inference attacks, i.e., inferring whether individuals' data have been used for training models. The lack of…