PNNL

Siddhartha Shankar Das is a postdoctoral researcher at Pacific Northwest National Laboratory. While earning a PhD from Purdue University, Das designed scalable algorithms for graph neural networks. With research interests broadly across the domains of graph-based machine learning, natural language processing, and cybersecurity, Das has also worked on classifying and analyzing software vulnerabilities into weaknesses and attack patterns by using large language models.

Google Scholar Profile

• Machine learning and deep learning
• Graph neural networks
• Large‑scale graph algorithms
• Natural language processing
• Large language models
• Cybersecurity
• Optimization and evolutionary algorithms
• Python, C++
• PyTorch/TensorFlow

• PhD in computer science, Purdue University
• MS in computer science and engineering, Bangladesh University of Engineering and Technology
• BS in computer science and engineering, Bangladesh University of Engineering and Technology

• Conference reviewer; KDD, ICML, DSAA, and others
• Journal reviewer; Evolutionary Computation, IEEE Transactions on Artificial Intelligence, and others

• Best Paper, 2022 IEEE International Symposium on Technologies for Homeland Security (HST), IEEE, 2022
• Best Application Paper, 2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA), IEEE, 2021

2025

• Siddhartha Shankar Das and Naheed Anjum Arafat and Muftiqur Rahman and S M Ferdous and Alex Pothen and Mahantesh M Halappanavar, SGS-GNN: A Supervised Graph Sparsification method for Graph Neural Networks, 2025, 2502.10208, https://arxiv.org/abs/2502.10208.

2024

• Siddhartha Shankar Das, S M Ferdous, Mahantesh M. Halappanavar, Edoardo Serra, and Alex Pothen. 2024. AGS-GNN: Attribute-guided Sampling for Graph Neural Networks. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '24). Association for Computing Machinery, New York, NY, USA, 538–549. https://doi.org/10.1145/3637528.3671940.

2022

• Halappanavar, Mahantesh, Das, Siddhartha S., Serra, Edoardo, Pothen, Alex, & Al-Shaer, Ehab. (2022, February 25). Cybersecurity-Tools/V2W-BERT. [Computer software]. https://github.com/Cybersecurity-Tools/V2W-BERT. https://doi.org/10.11578/dc.20240614.205.
• K. Panchal, S. S. Das, L. De La Torre, J. Miller, R. Rallo and M. Halappanavar, "Efficient Clustering of Software Vulnerabilities using Self Organizing Map (SOM)," 2022 IEEE International Symposium on Technologies for Homeland Security (HST), Boston, MA, USA, 2022, pages 1-7, doi: 10.1109/HST56032.2022.10025443.
• S. S. Das, M. Halappanavar, A. Tumeo, E. Serra, A. Pothen and E. Al-Shaer, "VWC-BERT: Scaling Vulnerability–Weakness–Exploit Mapping on Modern AI Accelerators," 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan, 2022, pages 1224-1229, doi: 10.1109/BigData55660.2022.10020622.
• S. S. Das, A. Dutta, S. Purohit, E. Serra, M. Halappanavar and A. Pothen, "Towards Automatic Mapping of Vulnerabilities to Attack Patterns using Large Language Models," 2022 IEEE International Symposium on Technologies for Homeland Security (HST), Boston, MA, USA, 2022, pp. 1-7, doi: 10.1109/HST56032.2022.10025459.

2019

• Siddhartha Shankar Das, Md Monirul Islam, Naheed Anjum Arafat, Evolutionary algorithm using adaptive fuzzy dominance and reference point for many-objective optimization, Swarm and Evolutionary Computation, Volume 44, 2019, Pages 1092-1107, ISSN 2210-6502, https://doi.org/10.1016/j.swevo.2018.11.003.