activity
20172026
most citedTowards Algorithmic Fairness in Space-Time: Filling in Black Holes

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.AI2026

Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability

Harsh Raj, Niranjan Orkat, Suvrorup Mukherjee +3

This paper establishes a rigorous measurement science for AI agent reliability, providing a foundational framework for quantifying consistency under semantically preserving perturb…

stat.AP2022★ 1 cited

Towards Algorithmic Fairness in Space-Time: Filling in Black Holes

Cheryl Flynn, Aritra Guha, Subhabrata Majumdar +2

New technologies and the availability of geospatial data have drawn attention to spatio-temporal biases present in society. For example: the COVID-19 pandemic highlighted dispariti…

stat.AP2021

Detecting Bias in the Presence of Spatial Autocorrelation

Subhabrata Majumdar, Cheryl Flynn, Ritwik Mitra

In spite of considerable practical importance, current algorithmic fairness literature lacks technical methods to account for underlying geographic dependency while evaluating or m…

cs.CR2020

Local Dampening: Differential Privacy for Non-numeric Queries via Local Sensitivity

Victor A. E. Farias, Felipe T. Brito, Cheryl Flynn +3

Differential privacy is the state-of-the-art formal definition for data release under strong privacy guarantees. A variety of mechanisms have been proposed in the literature for re…

cs.CY2020

Towards Integrating Fairness Transparently in Industrial Applications

Emily Dodwell, Cheryl Flynn, Balachander Krishnamurthy +2

Numerous Machine Learning (ML) bias-related failures in recent years have led to scrutiny of how companies incorporate aspects of transparency and accountability in their ML lifecy…

cs.DB2017

Composing Differential Privacy and Secure Computation: A case study on scaling private record linkage

Xi He, Ashwin Machanavajjhala, Cheryl Flynn +1

Private record linkage (PRL) is the problem of identifying pairs of records that are similar as per an input matching rule from databases held by two parties that do not trust one…