GNN-Based Predictive System Call Malware Detection: A Dynamic Behavior Graph Learning Approach

Abstract

Patent for a GNN-based predictive system call malware detection method using a dynamic behavior graph learning approach.

This work intersects with research areas including graph neural network, GNN, malware detection, system calls, dynamic behavior graph, cybersecurity, deep learning, and Indian patent. It is part of the broader research portfolio of Nitiraj V. Kulkarni in the domain of intellectual property and applied engineering.

Keywords & Topics

graph neural network, GNN, malware detection, system calls, dynamic behavior graph, cybersecurity, deep learning, Indian patent

How to Cite

APA

Nitiraj V. Kulkarni (2026). GNN-Based Predictive System Call Malware Detection: A Dynamic Behavior Graph Learning Approach. Patent Application, Indian Patent – Application No. 202621049886 – Publication Date: 15/05/2026. Indian Patent Office.

IEEE

Nitiraj V. Kulkarni, "GNN-Based Predictive System Call Malware Detection: A Dynamic Behavior Graph Learning Approach," Patent Application, Indian Patent – Application No. 202621049886 – Publication Date: 15/05/2026, 2026.

BibTeX

@article{2026_patent_gnn_system_call_malware_detection,
  title={GNN-Based Predictive System Call Malware Detection: A Dynamic Behavior Graph Learning Approach},
  author={Nitiraj V. Kulkarni},
  journal={Patent Application},
  year={2026},
  publisher={Indian Patent Office}
}

Identifiers & Links

Last updated: 2026-05-15

About the Author

Nitiraj V. Kulkarni is an AI safety and cybersecurity researcher based in Pune, India, with 35+ peer-reviewed publications, 5 patents, 6 copyright registrations, and 15,000+ open datasets published on Kaggle and Zenodo. He serves as a peer reviewer for 11+ international journals and conferences. Read full profile.