Udesh Kumarasinghe

Research Assistant @ SCoRe Lab.

udesh_kumarasinghe_profile.jpg

I am an aspiring Researcher who currently working as a Research Assistant. I have five years of experience working as a system engineer and a research engineer. My research interests are graph learning and network science where I have an understanding in a theoretical and practical standpoint. Though, I have also tackled problems in varying fields such as Cyber-Security, Natural Language Processing, and Cryptocurrency.

News

Dec 13, 2022 Honoured with the ICTA Award for the Best Computer Science Final Year Project.
Oct 9, 2022 First author paper “HeteroGuard: Defending Heterogeneous Graph Neural Networks against Adversarial Attacks” is accepted at The 2nd International Workshop on Machine Learning on Graphs (MLoG) to be held at ICDM’22.
Apr 27, 2022 Defended the bachelors thesis titled, “Adversarial Attacks for Malicious Domain Detection using Heterogeneous Information Networks”.
Mar 15, 2022 Submitted a pre-print version of the resource paper PDNS-Net.

Publications

  1. HeteroGuard: Defending Heterogeneous Graph Neural Networks against Adversarial Attacks
    U. Kumarasinghe, M. Nabeel, K. De Zoysa, and 2 more authors
    In 2022 IEEE International Conference on Data Mining Workshops (ICDMW) Dec 2022
  2. PDNS-Net: A Large Heterogeneous Graph Benchmark Dataset of Network Resolutions for Graph Learning
    Udesh Kumarasinghe, Fatih Deniz, and Mohamed Nabeel
    Mar 2022