2 papers
cs.CR2025
GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models
Zeyu Song, Ehsanul Kabir, Shagufta Mehnaz
Graph Neural Networks (GNNs) have become indispensable tools for learning from graph structured data, catering to various applications such as social network analysis and fraud det…
cs.LG2025
Disparate Privacy Vulnerability: Targeted Attribute Inference Attacks and Defenses
Ehsanul Kabir, Lucas Craig, Shagufta Mehnaz
As machine learning (ML) technologies become more prevalent in privacy-sensitive areas like healthcare and finance, eventually incorporating sensitive information in building data-…