12 citations · 78 across the 25 of their papers we have counts for
25 papers
Picture the Epsilon: Pursuing Identity-Level Privacy Guarantees for Images
Arman Zareian Jahromi, Vishnu Bondalakunta, Mohammad Akbar Bin Shah +3
Several methods for auditing privacy in embedding spaces report a number called "epsilon." The common name is misleading: one number may be a heuristic score, another may come from…
Toward Interpretable Privacy Guarantees in Face-Swapping Anonymization
Vishnu Bondalakunta, Arman Zareian Jahromi, Shuangqing Wei +1
Face-swapping has emerged as a promising approach to facial privacy protection, replacing a target individual's appearance with that of a donor while preserving non-facial context.…
Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4
Bishwas Mandal, George Amariucai, Shuangqing Wei
We investigate the application of large language models (LLMs), specifically GPT-4, to scenarios involving the tradeoff between privacy and utility in tabular data. Our approach en…
Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization
Bishwas Mandal, George Amariucai, Shuangqing Wei
We propose a novel problem formulation to address the privacy-utility tradeoff, specifically when dealing with two distinct user groups characterized by unique sets of private and…
Improving behavior based authentication against adversarial attack using XAI
Dong Qin, George Amariucai, Daji Qiao +1
In recent years, machine learning models, especially deep neural networks, have been widely used for classification tasks in the security domain. However, these models have been sh…
A Comprehensive and Reliable Feature Attribution Method: Double-sided Remove and Reconstruct (DoRaR)
Dong Qin, George Amariucai, Daji Qiao +2
The limited transparency of the inner decision-making mechanism in deep neural networks (DNN) and other machine learning (ML) models has hindered their application in several domai…