M. S. Vinay Data-verified
Affiliation confirmed via AI analysis of OpenAlex, ORCID, and web sources.
Researcher
unknown
Research Areas
Links
Biography and Research Information
OverviewAI-generated summary
M. S. Vinay's research focuses on the application of advanced machine learning techniques, particularly contrastive learning, for detecting insider threats and fraud. This work aims to develop more robust methods for identifying malicious activities within systems, even when dealing with noisy or incomplete data. Vinay has explored the use of in-context learning demonstrations for improving model performance, investigating how to select the most influential demonstrations for training.
Vinay has a publication record of five papers, with a citation count of 16 and an h-index of 3. Key collaborators include Xintao Wu and Minh-Hao Van from the University of Arkansas at Fayetteville, with whom Vinay has co-authored multiple publications. Vinay's recent activity indicates ongoing engagement in this research area.
Metrics
- h-index: 3
- Publications: 5
- Citations: 16
Selected Publications
-
Contrastive Learning for Fraud Detection from Noisy Labels (2024)
-
Robust Fraud Detection via Supervised Contrastive Learning (2023)
-
Contrastive Learning for Insider Threat Detection (2022)
Collaboration Network
Top Collaborators
- Contrastive Learning for Insider Threat Detection
- Robust Fraud Detection via Supervised Contrastive Learning
- In-Context Learning Demonstration Selection via Influence Analysis
- Robust Fraud Detection via Supervised Contrastive Learning
- Contrastive Learning for Fraud Detection from Noisy Labels
- Contrastive Learning for Insider Threat Detection
- Robust Fraud Detection via Supervised Contrastive Learning
- Robust Fraud Detection via Supervised Contrastive Learning
- Contrastive Learning for Fraud Detection from Noisy Labels
- In-Context Learning Demonstration Selection via Influence Analysis
Similar Researchers
Based on overlapping research topics