Alycia N. Carey Data-verified
Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.
Researcher
faculty
Research Areas
Links
Biography and Research Information
OverviewAI-generated summary
Alycia N. Carey's research investigates methods for enhancing the fairness and robustness of machine learning models, particularly in contexts involving sensitive data. Her work has explored techniques such as differential privacy to protect data utility while maintaining model accuracy, as seen in studies on DP-TabICL and the impact of local differential privacy on utility loss. Carey also examines approaches to ensure demographic fairness in federated learning settings and develops explainability methods for machine learning systems, exemplified by the SAGE Intrusion Detection System. Her publications include contributions to understanding statistical and causal fairness and the application of influence functions for robust training with noisy data, such as in brain MRI analysis. Carey collaborates with several researchers at the University of Arkansas at Fayetteville, including Minh-Hao Van and Xintao Wu.
Metrics
- h-index: 5
- Publications: 23
- Citations: 135
Selected Publications
-
Achieving Distributive Justice in Federated Learning via Uncertainty Quantification (2026)
-
Influence-based approaches for tumor classification in noisy brain MRI with deep learning and vision-language models (2025)
-
DP-TabICL: In-Context Learning with Differentially Private Tabular Data (2024)
-
Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions (2024)
-
Robust Influence-Based Training Methods for Noisy Brain MRI (2024)
-
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks (2023)
-
Randomized Response Has No Disparate Impact on Model Accuracy (2023)
-
Robust Personalized Federated Learning under Demographic Fairness Heterogeneity (2022)
-
The statistical fairness field guide: perspectives from social and formal sciences (2022)
-
The Causal Fairness Field Guide: Perspectives From Social and Formal Sciences (2022)
-
Adversarial attacks against image-based malware detection using autoencoders (2021)
Collaboration Network
Top Collaborators
- The statistical fairness field guide: perspectives from social and formal sciences
- The Causal Fairness Field Guide: Perspectives From Social and Formal Sciences
- Robust Personalized Federated Learning under Demographic Fairness Heterogeneity
- DP-TabICL: In-Context Learning with Differentially Private Tabular Data
- Randomized Response Has No Disparate Impact on Model Accuracy
Showing 5 of 12 shared publications
- Robust Influence-Based Training Methods for Noisy Brain MRI
- Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions
- HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks
- HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks
- Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions
Showing 5 of 7 shared publications
- DP-TabICL: In-Context Learning with Differentially Private Tabular Data
- Randomized Response Has No Disparate Impact on Model Accuracy
- DP-TabICL: In-Context Learning with Differentially Private Tabular Data
- The Fairness Field Guide: Perspectives from Social and Formal Sciences
- Evaluating the Impact of Local Differential Privacy on Utility Loss via Influence Functions
- Privacy-Preserving AutoML.
- Privacy-Preserving AutoML.
- DP-TabICL: In-Context Learning with Differentially Private Tabular Data
- DP-TabICL: In-Context Learning with Differentially Private Tabular Data
- Adversarial attacks against image-based malware detection using autoencoders
- Adversarial attacks against image-based malware detection using autoencoders
- Adversarial attacks against image-based malware detection using autoencoders
- SAGE Intrusion Detection System: Sensitivity Analysis Guided Explainability for Machine Learning.
- SAGE Intrusion Detection System: Sensitivity Analysis Guided Explainability for Machine Learning.
- SAGE Intrusion Detection System: Sensitivity Analysis Guided Explainability for Machine Learning.
- SAGE Intrusion Detection System: Sensitivity Analysis Guided Explainability for Machine Learning.
- SAGE Intrusion Detection System: Sensitivity Analysis Guided Explainability for Machine Learning.
- SAGE Intrusion Detection System: Sensitivity Analysis Guided Explainability for Machine Learning.
Similar Researchers
Based on overlapping research topics