Murat Kantarcioglu

Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation

FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments

Judging with Confidence: Calibrating Autoraters to Preference Distributions

MIAU: Membership Inference Attack Unlearning Score for Quantifying the Forgetting Quality of Unlearning Methods

GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits Learning

ProvCreator: Synthesizing Graph Data with Text Attributes

FLAG: Clustered Federated Learning Combining Data and Gradient Information in Heterogeneous Settings