Michael Mandulak

Michael Mandulak

Auto-generated profile, based on publicly available information

Michael Mandulak

RPI, Troy, NY, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 November 2024
Verified
Conference Paper
Open access
YZYuxuan Zhu
Yuxuan Zhu
MMMichael Mandulak
Michael Mandulak
KWKerui Wu
Kerui Wu
GSGeorge M. Slota
George M. Slota
YJYuseok Jeon
Yuseok Jeon
LYLei Yu
Lei Yu
Graph Neural Networks (GNNs) have been shown to be susceptible to backdoor poisoning attacks, which pose serious threats to real-world applications. Meanwhile, graph reduction techniques have recently emerged as effective methods for accelerating GNN training on large-scale graphs. However, the development of graph reduction techniques for large graphs does not yet address how these methods might interact with the potential risks of data poisoning attacks against GNNs, particularly in relation to existing backdoor attacks. This paper conducts a thorough examination of the robustness of graph reduction methods in scalable GNN training in the presence of state-of-the-art backdoor attacks. We performed a comprehensive robustness analysis across six coarsening methods and six sparsification methods for graph reduction, under three GNN backdoor attacks against three GNN architectures. Our findings indicate that the effectiveness of graph reduction methods in mitigating attack success rates varies significantly, with some methods even exacerbating the attacks. Through detailed analyses of triggers and poisoned nodes, we interpret our findings and enhance our understanding of how graph reduction influences robustness against backdoor attacks. These results highlight the critical need for incorporating robustness considerations in graph reduction for scalable GNN training.

8 September 2025
Verified
Conference Paper
Open access
GSGeorge M. Slota
George M. Slota
MMMichael Mandulak
Michael Mandulak