Situated Anomaly Detection in an Open Environment. This project aims to investigate situated anomaly detection in an open environment. Existing anomaly detection techniques follow the setting of conventional machine learning and discover anomalies from a set of collected data. In contrast, this project proposes to develop the next-generation of anomaly detection algorithms by learning from interactions with an open environment, which enables the discovery of new anomalies and the early detection ....Situated Anomaly Detection in an Open Environment. This project aims to investigate situated anomaly detection in an open environment. Existing anomaly detection techniques follow the setting of conventional machine learning and discover anomalies from a set of collected data. In contrast, this project proposes to develop the next-generation of anomaly detection algorithms by learning from interactions with an open environment, which enables the discovery of new anomalies and the early detection of anomalies. The established theories and developed algorithms will advance frontier technologies in machine intelligence. The success of the project will contribute to a wide range of real applications in cybersecurity, defence and finance, bringing massive social and economic benefits. Read moreRead less
Rethinking Topological Persistence. This project aims to address the lack of transferability and uncertainty-awareness in AI models. Despite their success, AI models are met with bias and uncertainty when deployed in the real world. As a result, they are rarely used in high-risk industries like cybersecurity or transport. This project expects to build uncertainty-awareness into models by teaching them to return UNKNOWN when they encounter a previously unseen thing, instead of misclassifying it. ....Rethinking Topological Persistence. This project aims to address the lack of transferability and uncertainty-awareness in AI models. Despite their success, AI models are met with bias and uncertainty when deployed in the real world. As a result, they are rarely used in high-risk industries like cybersecurity or transport. This project expects to build uncertainty-awareness into models by teaching them to return UNKNOWN when they encounter a previously unseen thing, instead of misclassifying it. Further, the evaluation methods to be developed will not rely on access to test data, allowing cost-effective, private, and safe AI for high-stakes decision support. The outcomes will benefit Australia by accelerating economic investment and fostering greater social acceptance of AI.Read moreRead less
Readying Wireless Networks for Future Communications Systems: From Ubiquitous Computing to the Internet of Things. This project aims to prepare wireless networks for future communications systems, by improving the data transmission rates of wireless networks, through developing new coding schemes based on the synergy of noisy-channel coding and index coding. This will allow wireless networks, used in conjunction with the fibre-optic National Broadband Network, to support future high-data-rate an ....Readying Wireless Networks for Future Communications Systems: From Ubiquitous Computing to the Internet of Things. This project aims to prepare wireless networks for future communications systems, by improving the data transmission rates of wireless networks, through developing new coding schemes based on the synergy of noisy-channel coding and index coding. This will allow wireless networks, used in conjunction with the fibre-optic National Broadband Network, to support future high-data-rate and ubiquitous communication services. This project aims to produce new theoretical results in the field of communication theory, and efficient practical coding schemes for wireless communications.Read moreRead less
Deep Interaction Learning in Unlabelled Big Data and Complex Systems. This project aims to effectively model intricate interactions deeply embedded in unlabelled big data and complex systems, which are often hierarchical, heterogeneous, contextual, dynamic or even contrastive. Learning such interactions is the keystone of robust data science and for realizing the value of big data but it poses significant challenges and knowledge gaps to existing data analytics and learning systems. The expected ....Deep Interaction Learning in Unlabelled Big Data and Complex Systems. This project aims to effectively model intricate interactions deeply embedded in unlabelled big data and complex systems, which are often hierarchical, heterogeneous, contextual, dynamic or even contrastive. Learning such interactions is the keystone of robust data science and for realizing the value of big data but it poses significant challenges and knowledge gaps to existing data analytics and learning systems. The expected outcomes include new-generation theories and methods for the unsupervised learning of complex interactions in real-life big data, which are anticipated to enable the intrinsic processing of big data complexities and substantially enhance Australia’s leadership in frontier data science research and applications. Read moreRead less
Ultimately Trusted Security through Human-Powered Cryptography. Cryptography offers wonderful tools for unbreakable data security, but only between computer nodes, leaving their human owners helpless. Encrypted tunnels terminate not at humans but at mobile phones and personal computers, exposing users' secrets to spyware from search-engine keyloggers to full-bore malware planted by crooks, hackers, and foreign spy agencies. This project aims to create a simple and strong cryptography, so that hu ....Ultimately Trusted Security through Human-Powered Cryptography. Cryptography offers wonderful tools for unbreakable data security, but only between computer nodes, leaving their human owners helpless. Encrypted tunnels terminate not at humans but at mobile phones and personal computers, exposing users' secrets to spyware from search-engine keyloggers to full-bore malware planted by crooks, hackers, and foreign spy agencies. This project aims to create a simple and strong cryptography, so that humans can, for the first time, take front seat in real security protocols. The technical challenge is to build public-key ciphers, operable manually from a mental key in seconds, and from there remake human-powered versions of many useful information security protocols.Read moreRead less
Automatic video annotation by learning from web data. This project aims to study next-generation video annotation technologies to automatically tag raw videos using a huge set of semantic concepts. The project will study new domain adaptation schemes and frameworks in order to substantially improve video annotation performance. The resulting prototype system can be directly used by ordinary users worldwide to search their personal videos using textual queries. The system is also applicable to vi ....Automatic video annotation by learning from web data. This project aims to study next-generation video annotation technologies to automatically tag raw videos using a huge set of semantic concepts. The project will study new domain adaptation schemes and frameworks in order to substantially improve video annotation performance. The resulting prototype system can be directly used by ordinary users worldwide to search their personal videos using textual queries. The system is also applicable to video surveillance applications, which can enhance Australia’s homeland security.Read moreRead less
Enabling Automatic Graph Learning Pipelines with Limited Human Knowledge. This project aims to develop an automatic graph learning system for complex graph data analysis. Machine learning for graph data commonly requires significant human knowledge from both domain professionals as well as algorithm experts, rendering existing systems ineffective and unexplainable. This project expects to design novel graph learning techniques which automatically infer graph relations, learn graph models, adapts ....Enabling Automatic Graph Learning Pipelines with Limited Human Knowledge. This project aims to develop an automatic graph learning system for complex graph data analysis. Machine learning for graph data commonly requires significant human knowledge from both domain professionals as well as algorithm experts, rendering existing systems ineffective and unexplainable. This project expects to design novel graph learning techniques which automatically infer graph relations, learn graph models, adapts existing knowledge to new domains, and provide explanations to the graph learning system. The research results should provide benefit to governments and businesses in many critical applications, such as bioassay activity prediction, credit assessment, and drug discovery and vaccine development in response to the pandemic.Read moreRead less
Advanced search of cohesive subgraphs in big graphs. This project aims to study advanced cohesive subgraph searches, as well as design efficient and scalable techniques to conduct such searches. Cohesive subgraph search over big graphs is demanded by many applications, such as risk management, analysis of users’ behaviours, cybersecurity, crime detection, social marketing and community search. This project will develop, analyse, implement, and evaluate novel indexing and data processing techniqu ....Advanced search of cohesive subgraphs in big graphs. This project aims to study advanced cohesive subgraph searches, as well as design efficient and scalable techniques to conduct such searches. Cohesive subgraph search over big graphs is demanded by many applications, such as risk management, analysis of users’ behaviours, cybersecurity, crime detection, social marketing and community search. This project will develop, analyse, implement, and evaluate novel indexing and data processing techniques to support a set of advanced cohesive subgraph searches. This will provide significant benefits to many applications such as the next generation of fintech, cybersecurity, e-commerce, crime detection and social network analysis.Read moreRead less
Smart Wireless Radio Environments for the 6G Era. This project aims to revolutionise radio signal propagation and information transfer by developing “smart” wireless radio environments. Using Reconfigurable Intelligent Surface (RIS), the smart wireless network can transmit information without generating new signals but recycling the incoming signal. However, as an emerging technology, fundamental analysis – in terms of rate, reliability, and efficiency – is needed to understand the performance o ....Smart Wireless Radio Environments for the 6G Era. This project aims to revolutionise radio signal propagation and information transfer by developing “smart” wireless radio environments. Using Reconfigurable Intelligent Surface (RIS), the smart wireless network can transmit information without generating new signals but recycling the incoming signal. However, as an emerging technology, fundamental analysis – in terms of rate, reliability, and efficiency – is needed to understand the performance of RIS-empowered wireless networks. Expected outcomes include new communication-theoretic models and the enabling technologies to realise them in practice. These smart environments have the potential to offer “greener” and more "seamless wireless connectivity" for the future wireless network.Read moreRead less
The many lives and deaths of high redshift massive quiescent galaxies. This Fellowship will investigate the recent discovery of very massive, extremely early forming quiescent galaxies and explain their exceptional origin, death, and ultimate place in the local Universe. It is a multidisciplinary project that seeks to produce new knowledge using high-performance computing, software engineering, and sophisticated data analysis techniques. Expected outcomes include novel and improved supercomputer ....The many lives and deaths of high redshift massive quiescent galaxies. This Fellowship will investigate the recent discovery of very massive, extremely early forming quiescent galaxies and explain their exceptional origin, death, and ultimate place in the local Universe. It is a multidisciplinary project that seeks to produce new knowledge using high-performance computing, software engineering, and sophisticated data analysis techniques. Expected outcomes include novel and improved supercomputer simulations of several billions of galaxies processed through a virtual observatory, providing tools and fundamental knowledge for observational, theoretical, and computational astrophysics.Read moreRead less