no code implementations • 18 Sep 2023 • Nathasha Naranpanawa, H. Peter Soyer, Adam Mothershaw, Gayan K. Kulatilleke, ZongYuan Ge, Brigid Betz-Stablein, Shekhar S. Chandra
An ugly duckling is an obviously different skin lesion from surrounding lesions of an individual, and the ugly duckling sign is a criterion used to aid in the diagnosis of cutaneous melanoma by differentiating between highly suspicious and benign lesions.
1 code implementation • 28 Apr 2023 • Liam Daly Manocchio, Siamak Layeghy, Wai Weng Lo, Gayan K. Kulatilleke, Mohanad Sarhan, Marius Portmann
This paper presents the FlowTransformer framework, a novel approach for implementing transformer-based Network Intrusion Detection Systems (NIDSs).
1 code implementation • 15 Dec 2022 • Gayan K. Kulatilleke, Shekhar S. Chandra, Marius Portmann
An author style detection task is a metric learning problem, where learning style features with small intra-class variations and larger inter-class differences is of great importance to achieve better performance.
1 code implementation • 28 Sep 2022 • Gayan K. Kulatilleke, Marius Portmann, Shekhar S. Chandra
In this work, we propose a meta-node based approximation technique that can (a) proxy all negative combinations (b) in quadratic cluster size time complexity, (c) at graph level, not node level, and (d) exploit graph sparsity.
no code implementations • 25 Aug 2022 • Gayan K. Kulatilleke, Sugandika Samarakoon
In this work, we develop a theoretical foundation to model human annotation errors and extreme imbalance typical in real world fraud detection data sets.
no code implementations • 25 Aug 2022 • Gayan K. Kulatilleke
Machine learning has opened up new tools for financial fraud detection.
no code implementations • 20 Aug 2022 • Gayan K. Kulatilleke
Given past transactions, a machine learning algorithm has the ability to 'learn' infinitely complex characteristics in order to identify frauds in real-time, surpassing the best human investigators.
no code implementations • 19 Jul 2022 • Wai Weng Lo, Gayan K. Kulatilleke, Mohanad Sarhan, Siamak Layeghy, Marius Portmann
The proposed model comprises a botnet detector and an explainer for automatic forensics.
1 code implementation • 27 Apr 2022 • Gayan K. Kulatilleke, Marius Portmann, Shekhar S. Chandra
We also propose SCGC*, with a more effective, novel, Influence Augmented Contrastive (IAC) loss to fuse richer structural information, and half the original model parameters.
no code implementations • 20 Mar 2022 • Wai Weng Lo, Gayan K. Kulatilleke, Mohanad Sarhan, Siamak Layeghy, Marius Portmann
The proposed method was evaluated on the Elliptic dataset and shows that our approach outperforms the state-of-the-art in terms of key classification metrics, which demonstrates the potential of self-supervised GNN in the detection of illicit cryptocurrency transactions.
1 code implementation • 21 Oct 2021 • Gayan K. Kulatilleke, Marius Portmann, Ryan Ko, Shekhar S. Chandra
While Graph Neural Networks have gained popularity in multiple domains, graph-structured input remains a major challenge due to (a) over-smoothing, (b) noisy neighbours (heterophily), and (c) the suspended animation problem.
Ranked #3 on Node Classification on Pubmed Full-supervised