Deep Learning Attacks and Active Defences: A Cybersecurity Perspective. The belief that deep learning technology is imperative for economic development, military control, and strategic competitiveness has accelerated its development across the globe. However, experience has revealed the disappointing fact that deep learning models are vulnerable to a range of security attacks. Hence, a series of methodologies and defence strategies will be devised that make deep learning systems robust to these ....Deep Learning Attacks and Active Defences: A Cybersecurity Perspective. The belief that deep learning technology is imperative for economic development, military control, and strategic competitiveness has accelerated its development across the globe. However, experience has revealed the disappointing fact that deep learning models are vulnerable to a range of security attacks. Hence, a series of methodologies and defence strategies will be devised that make deep learning systems robust to these attacks. The methodologies require analysing attack lifecycles to identify them in their early stages. With this knowledge, active defence methods and forensic strategies can be developed to ensure efficient defences and prevent further attacks. Moreover, the outputs will be generalisable to most deep learning services.Read moreRead less
Balance and reinforcement: privacy and fairness in high intelligence models. The aim of this project is to develop a series of privacy preservation methods to achieve a new balance between privacy and fairness in highly accurate intelligence models. The main issue in achieving this goal is that high-accuracy intelligence technologies have resulted in significant privacy violations and are very vulnerable to issues of unfairness. This project will analyse the privacy risks associated with intelli ....Balance and reinforcement: privacy and fairness in high intelligence models. The aim of this project is to develop a series of privacy preservation methods to achieve a new balance between privacy and fairness in highly accurate intelligence models. The main issue in achieving this goal is that high-accuracy intelligence technologies have resulted in significant privacy violations and are very vulnerable to issues of unfairness. This project will analyse the privacy risks associated with intelligent systems and devise mechanisms to mutually reinforce both privacy and fairness based on the theoretical foundations laid by our analysis. These outcomes will enable model owners to effectively protect their intellectual property and offer services to users in a private, fair, and accurate manner.Read moreRead less
Knowledge Graph-driven Software Vulnerability Risk Discovery and Assessment. This project aims to alleviate cyberattacks which are increasingly being crafted to attack software vulnerabilities and weaknesses by utilising advanced knowledge graphs and deep learning techniques. This project expects to construct an innovative software vulnerability knowledge graph and develop advanced graph-based algorithms and models. Expected outcomes of this project include the enhanced capacity to defend agains ....Knowledge Graph-driven Software Vulnerability Risk Discovery and Assessment. This project aims to alleviate cyberattacks which are increasingly being crafted to attack software vulnerabilities and weaknesses by utilising advanced knowledge graphs and deep learning techniques. This project expects to construct an innovative software vulnerability knowledge graph and develop advanced graph-based algorithms and models. Expected outcomes of this project include the enhanced capacity to defend against cyberattacks for both organisations and individuals in Australia and beyond, theory development in graph theory, refined graph neural network models and improved graph transfer learning algorithms.Read moreRead less
Bridging the gap between Key-Evolving Signatures and Their Applications. This project aims to address the gap between cryptography primitives and their applications. Key-evolution signatures are effective in resolving secret key compromises. Theoretically, they can be adopted to secure Proof-of-Stake in blockchain against long-range attacks. Unfortunately, there are many remaining issues to address that make adoption insecure. This project is significant since it will enrich theoretical cryptogr ....Bridging the gap between Key-Evolving Signatures and Their Applications. This project aims to address the gap between cryptography primitives and their applications. Key-evolution signatures are effective in resolving secret key compromises. Theoretically, they can be adopted to secure Proof-of-Stake in blockchain against long-range attacks. Unfortunately, there are many remaining issues to address that make adoption insecure. This project is significant since it will enrich theoretical cryptography contributions and ensure their practical and secure applications. The expected outcomes are innovative technologies, guaranteeing security whilst solving real-life problems. The project will deliver significant and innovative technology for enabling effective and secure blockchain systems. Read moreRead less
Advanced Machine Learning with Bilevel Optimization. There is an urgent need to develop a new machine learning (ML) paradigm that can overcome data-privacy and model-size constraints in real-world applications. This project aims to develop an advanced paradigm of ML with bilevel optimisation, called bilevel ML. A theoretically-guaranteed fast approximate solver and a new fuzzy bilevel learning framework will be developed to achieve the aim in complex situations; a methodology to transfer knowled ....Advanced Machine Learning with Bilevel Optimization. There is an urgent need to develop a new machine learning (ML) paradigm that can overcome data-privacy and model-size constraints in real-world applications. This project aims to develop an advanced paradigm of ML with bilevel optimisation, called bilevel ML. A theoretically-guaranteed fast approximate solver and a new fuzzy bilevel learning framework will be developed to achieve the aim in complex situations; a methodology to transfer knowledge and an approach to fast-adapt bilevel optimization solutions when required computing resources change. The anticipated outcomes should significantly improve the reliability of ML with benefits for safety learning and computing resource optimisation in ML-based data analytics.Read moreRead less
Inference for Hawkes processes with challenging data. The Hawkes processes are statistical models for the analysis of high-impact event sequences, such as bushfires, earthquakes, infectious diseases, and cyber attacks. When the times and/or marks are missing for some events or when the data is otherwise incomplete, it is challenging to fit these models and perform diagnostic checks on the fitted models. This project aims to develop novel statistical methods to fit these models in the presence of ....Inference for Hawkes processes with challenging data. The Hawkes processes are statistical models for the analysis of high-impact event sequences, such as bushfires, earthquakes, infectious diseases, and cyber attacks. When the times and/or marks are missing for some events or when the data is otherwise incomplete, it is challenging to fit these models and perform diagnostic checks on the fitted models. This project aims to develop novel statistical methods to fit these models in the presence of incomplete data and to check the goodness-of-fit of the fitted models. The expected outcomes include publications documenting these methods and software packages implementing them. The primary benefits include the advancement of statistical methodology and the training of junior research personnel. Read moreRead less
Exploiting Geometries of Learning for Fast, Adaptive and Robust AI. This project aims to uniquely exploit geometric manifolds in deep learning to advance the frontier of Artificial Intelligence (AI) research and applications in cybersecurity and general cognitive tasks. It expects to develop new theories, algorithms, tools, and technologies for machine learning systems that are fast, adaptive, lifelong and robust, even with limited supervision. Expected outcomes will enhance Australia's capabili ....Exploiting Geometries of Learning for Fast, Adaptive and Robust AI. This project aims to uniquely exploit geometric manifolds in deep learning to advance the frontier of Artificial Intelligence (AI) research and applications in cybersecurity and general cognitive tasks. It expects to develop new theories, algorithms, tools, and technologies for machine learning systems that are fast, adaptive, lifelong and robust, even with limited supervision. Expected outcomes will enhance Australia's capability and competitiveness in AI, and deliver robust and trustworthy learning technology. The project should provide significant benefits not only in advancing scientific and translational knowledge but also in accelerating AI innovations, safeguarding cyberspace, and reducing the burden on defence expenses in Australia.Read moreRead less