2025-12-13 –, Rookie Track 2
Decentralised finance has seen explosive growth, but this has introduced new challenges in detecting illicit activity on public blockchains. My dissertation explored whether it's possible to build a real-time risk assessment system for DeFi transactions using Graph Neural Networks to identify suspicious patterns before transactions are processed. I analysed over 70 major crypto exploits and developed a labelled dataset of laundering behaviours, including mixer usage and peeling chains. Several machine learning models were tested, with Graph Isomorphism Networks showing the strongest performance. While results were promising, they also revealed practical limitations: even small false positive rates could disrupt millions of legitimate daily transactions. As a result, I propose hybrid AI-human systems and post-transaction monitoring as more viable near-term solutions. This talk will walk through my journey building the system, what worked, what didn’t, and the future of ML for DeFi compliance and blockchain security.
This research explored the viability of using Graph Neural Networks (GNNs) for detecting money laundering in DeFi ecosystems by analysing over 70 major crypto exploits. A labelled dataset was created, consisting of known laundering techniques such as peeling chains, dusting, and mixer interactions with legitimate blockchain activity. Among the models tested, Graph Isomorphism Networks (GIN) delivered the strongest results, significantly outperforming traditional approaches like Random Forest by 15–35% across key metrics. However, while the model achieved up to 95% precision, it still falls short of the near-perfect accuracy (99.99%) needed for fully autonomous transaction blocking in high-volume environments like Ethereum.
Inference performance is real-time capable (<0.15s), with the main bottleneck being third-party API limitations that I faced. Future work includes expanding the dataset with more diverse laundering patterns and cross-chain data, running a dedicated Ethereum node for low-latency access, and enhancing model performance through advanced architectures or ensemble learning. Including human-in-the-loop feedback and adversarial robustness will also be crucial to adapting to evolving threats. Finally, the methodology should be extended and validated across other blockchains such as Bitcoin, Solana, etc to ensure broader applicability in DeFi ecosystems.
MSc Cyber Security | Passionate about Web3 security and decentralised futures