{"links":{"self":"http://dataportal.arc.gov.au/NCGP/API/grants/DE260101172"},"data":{"type":"grant-details","id":"DE260101172","attributes":{"code":"DE260101172","administering-organisation":"Griffith University","announcement-administering-organisation":"Griffith University","scheme-name":"Discovery Early Career Researcher Award","grant-status":"Active","funding-commencement-year":2026,"years-funded":3,"project-start-date":"2026-02-01","anticipated-end-date":"2029-01-31","grant-summary":"Towards Unified Learning Framework for Graph Anomaly Detection. This project aims to build a unified framework to detect anomalies in networked data, such as fraud in financial systems or cyberattacks in computer networks. Existing solutions heavily rely on domain-specific data and costly computations to establish scenario-specific models, significantly limiting their applicability and generalisability in data-scarce, privacy-sensitive, or rapidly evolving scenarios. This project expects to design novel techniques to build a unified framework that can generalise across different application domains, data types, and anomaly types. The framework should benefit domains like finance, cybersecurity, and environmental monitoring, enhancing security and efficiency for governments, businesses, and communities.","funding-current":500386.00,"funding-at-announcement":496368,"investigators-current":[{"title":"Dr","firstName":"Yixin","familyName":"Liu","roleName":"Discovery Early Career Researcher Award","roleCode":"DECRA","isFellowship":true,"orcidIdentifier":"0000-0002-4309-5076 "}],"investigators-at-announcement":[{"title":"Dr","firstName":"Yixin","familyName":"Liu","roleName":"Discovery Early Career Researcher Award","roleCode":"DECRA","isFellowship":true,"orcidIdentifier":"0000-0002-4309-5076 "}],"organisations-current":[{"organisationName":"Griffith University","roleName":"Administering Organisation","state":"QLD"}],"organisations-at-announcement":[{"organisationName":"Griffith University","roleName":"Administering Organisation","state":"QLD"}],"field-of-research":[{"isPrimary":true,"code":"4605","name":"Data Management and Data Science","type":"FOR20"},{"isPrimary":false,"code":"460502","name":"Data Mining and Knowledge Discovery","type":"FOR20"}],"socio-economic-objective":[{"code":"220403","name":"Artificial Intelligence","type":"SEO20"},{"code":"280115","name":"Expanding Knowledge In the Information and Computing Sciences","type":"SEO20"}],"international-collaboration":["Singapore","United States of America"],"lief-register":[],"achievement-summary":null,"national-interest-test-statement":"Australians are currently facing a serious challenge—detecting abnormal activities in networked data, such as fraudulent behaviours and cyberattacks. For example, over $10 billion in laundered money per year urgently needs to be detected to help stabilise the economy and reduce long-term costs. The most effective solution to the challenge lies in graph-powered artificial intelligence techniques. However, current solutions are limited to detecting a single type of anomaly (e.g., suspicious transactions or accounts) and struggle to consider complex data patterns, such as heterogeneity (e.g., different account types) and dynamics (e.g., evolving transaction patterns).\n\nThis project will develop game-changing unified tools to accurately detect anomalies of any type, with various complex patterns, and from networked data across domains. The immediate applications in anti-money laundering, environmental monitoring, and cybersecurity are urgent and vital for Australian organisations and governments. This project will deliver fundamental knowledge for understanding complex anomalies in the Australian private and public sectors. The developed tools will reduce financial risks for businesses by millions of dollars.\n\nTo maximise the adoption of research outcomes, this project will actively involve industry partners and government agencies to integrate the tools into real-world systems. Open-source software will also be developed to facilitate the applications in broader sectors."}}}