Enhancing Illicit Activity Detection using XAI: A Multimodal Graph-LLM Framework

Financial cybercrime prevention is an increasing issue with many organisations and governments. As deep learning models have progressed to identify illicit activity on various financial and social networks, the explainability behind the model decisions has been lacklustre with the investigative analyst at the heart of any deep learning platform. In our paper, we present a state-of-the-art, novel multimodal proactive approach to addressing XAI in financial cybercrime detection. We leverage a triad of deep learning models designed to distill essential representations from transaction sequencing, subgraph connectivity, and narrative generation to significantly streamline the analyst's investigative process. Our narrative generation proposal leverages LLM to ingest transaction details and output contextual narrative for an analyst to understand a transaction and its metadata much further.

A Simplistic Machine Learning Approach to Contact Tracing

This report is based on the modified NIST challenge, Too Close For Too Long, provided by the SFI Centre for Machine Learning (ML-Labs). The modified challenge excludes the time calculation (too long) aspect. By handcrafting features from phone instrumental data we develop two machine learning models, a GBM and an MLP, to estimate distance between two phones. Our method is able to outperform the leading NIST challenge result by the Hong Kong University of Science and Technology (HKUST) by a significant margin.