Alycia N. Carey Source Confirmed

Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.

Researcher

University of Arkansas at Fayetteville

faculty

5 h-index 23 pubs 127 cited

Research Areas

Links

ORCID Research Group

Is this your profile? Verify and claim your profile

OverviewAI-generated summary

Alycia N. Carey's research focuses on machine learning, particularly in the areas of fairness, privacy, and interpretability. Her work addresses challenges in applying machine learning models to sensitive data, such as in healthcare or social science contexts. Carey has investigated methods to ensure statistical fairness and causal fairness in machine learning algorithms, aiming to mitigate biases that can arise in personalized learning systems. She also explores the impact of privacy-preserving techniques, like local differential privacy, on the utility and accuracy of machine learning models, specifically examining how these methods affect data sensitivity and model performance.

Her publications include work on robust federated learning under demographic fairness heterogeneity, in-context learning with differentially private tabular data, and sensitivity analysis for explainable AI systems. Carey has also studied the influence of local differential privacy on utility loss through influence functions and developed robust training methods for noisy brain MRI data. Her scholarship metrics include an h-index of 5 with 23 total publications and 127 citations. Carey collaborates with researchers at the University of Arkansas at Fayetteville, including Minh-Hao Van and Xintao Wu.

Metrics

h-index: 5
Publications: 23
Citations: 127

Selected Publications

Influence-based approaches for tumor classification in noisy brain MRI with deep learning and vision-language models (2025) DOI
DP-TabICL: In-Context Learning with Differentially Private Tabular Data (2024) DOI
Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions (2024) DOI
Robust Influence-Based Training Methods for Noisy Brain MRI (2024) DOI
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks (2023) DOI
Randomized Response Has No Disparate Impact on Model Accuracy (2023) DOI
Robust Personalized Federated Learning under Demographic Fairness Heterogeneity (2022) DOI
The statistical fairness field guide: perspectives from social and formal sciences (2022) DOI
The Causal Fairness Field Guide: Perspectives From Social and Formal Sciences (2022) DOI
Adversarial attacks against image-based malware detection using autoencoders (2021) DOI