Ants, bees and birds may help create an AI model that can identify and track blockchain money laundering, according to new Australian research.
The AI model is being researched by Charles Darwin University (CDU) as a way of better identifying anonymous, fast-moving, and cross-border blockchain money laundering and terrorist financing.
CDU engineering and IT lecturer Dr Reem Sherif says a swarm-based agentic AI model could render the identification of illegal cash flow more scalable, auditable and resilient.
Inspired by species such as ants, the model taps into simpler behaviour such as decentralised co-ordination and simple rules that result in more complex behaviour.
SOCIAL ROLES OF ANTS MAY BE DUPLICATED
The CDU says that the social make-up of ants can be broken into queen, workers, soldiers, and males, each of them with a single role to perform for the colony.
Similarly, one AI model might serve as ‘worker’ and another as ‘soldier’ to complete a specific task that creates a system capable of tracking blockchain money laundering.
Dr Sherif says they are studying how a team of five specialty AI agents can work together to detect suspicious transactions more effectively than traditional anti-money laundering (AML) models.
“Rather than rely on a single AI model, our framework assigns different AI agents to specific tasks such as analysing transaction flows, modelling relationships between accounts, and tracking suspicious activity,” she says.
“By combining multi-agent artificial intelligence with blockchain technology, we aim to improve the accuracy and explainability of automated money laundering detection, help financial institutions identify (illegal) activities (and) maintain a clear audit trail.
“Together, they provide a more adaptive and transparent approach to anti-money laundering.”
Dr Sherif says it is crucial to strengthen the AI swarm’s integration into compliance tools and that further refining is needed for better jurisdictional interoperability.
“As digital financial systems continue to evolve, intelligent collaborative AI systems have the potential to strengthen regulatory compliance and support faster, more reliable detection of financial crime,” she says.
Click here to read the research that has been published online.
RELATED STORIES
