MemberGuard: Protecting Machine Learning Privacy from Membership Inference. Machine Learning has become a core part of many real-world applications. However, machine learning models are vulnerable to membership inference attacks. In these attacks, an adversary can infer if a given data record has been part of the model's training data. In this project, the team aims to develop new techniques that can be used to counter these attacks, such as 1) new analytical models for membership leakage, 2) ne ....MemberGuard: Protecting Machine Learning Privacy from Membership Inference. Machine Learning has become a core part of many real-world applications. However, machine learning models are vulnerable to membership inference attacks. In these attacks, an adversary can infer if a given data record has been part of the model's training data. In this project, the team aims to develop new techniques that can be used to counter these attacks, such as 1) new analytical models for membership leakage, 2) new methods for susceptibility diagnosis, 3) new defences that leverage privacy and utility. Data-oriented services are estimated to be valuable assets in the future. These techniques can help Australia gain cutting edge advantage in machine learning security and privacy and protect its intellectual property on these services.Read moreRead less
Large-scale three dimensional deformation of the lithosphere by subduction and mantle flow. We will be modelling of the dynamics of the Earth's crust and shallow lithosphere in response to the huge stresses created by plate motions. For Australia these stresses are transmitted from the distant plate boundaries, but they have a direct controlling influence on the evolution of the petroleum rich basins of Australia. These basins have reached maturity; further exploration will be in deep water wher ....Large-scale three dimensional deformation of the lithosphere by subduction and mantle flow. We will be modelling of the dynamics of the Earth's crust and shallow lithosphere in response to the huge stresses created by plate motions. For Australia these stresses are transmitted from the distant plate boundaries, but they have a direct controlling influence on the evolution of the petroleum rich basins of Australia. These basins have reached maturity; further exploration will be in deep water where geophysical prospecting methods are unreliable. Model-driven "exploration geodynamics" methods such as those we are developing will be needed to support traditional exploration techniques in these areas.Read moreRead less
Privacy-preserving data processing on the cloud. This project aims to address the current lack of privacy of user data processed by common cloud computing web servers, including email, business data, and confidential files. This project aims to develop new techniques in cryptography. The anticipated outcome is a suite of practical tools enabling common cloud computing processing operations such as search, statistical analysis, and multi-user access control, to be performed efficiently while pres ....Privacy-preserving data processing on the cloud. This project aims to address the current lack of privacy of user data processed by common cloud computing web servers, including email, business data, and confidential files. This project aims to develop new techniques in cryptography. The anticipated outcome is a suite of practical tools enabling common cloud computing processing operations such as search, statistical analysis, and multi-user access control, to be performed efficiently while preserving the data privacy. These tools should provide significant benefits to the privacy of cloud users, as well as financial and reputation benefits to the IT industry, by significantly reducing the likelihood of massive user data privacy breaches in the event of a cyber-hacking attack on the cloud server.Read moreRead less
Finding and exploiting interesting paths in multidimensional information spaces. This project will invent a new approach for searching within a large complex information space, finding interesting paths between points within the space, visualising the results, and supporting rich, human-centric user interaction with queries and results. This project will embody these techniques in a novel, internet-scale framework to support rapid development of large path search and visualisation applications. ....Finding and exploiting interesting paths in multidimensional information spaces. This project will invent a new approach for searching within a large complex information space, finding interesting paths between points within the space, visualising the results, and supporting rich, human-centric user interaction with queries and results. This project will embody these techniques in a novel, internet-scale framework to support rapid development of large path search and visualisation applications. Evaluation will be via development of several exemplar applications. The techniques and framework will be applicable to a broad range of economically important problems in areas as diverse as health, travel, scientific publication search, product marketing and software engineering.Read moreRead less
Semantic Vectorisation: From Bitmaps to Intelligent Representations. The objective of this innovative project is to provide a solution to the open question of representing natural images by semantically rich vector graphics. The challenges are to identify key visual and temporal elements for images and videos, and efficiently decompose the visual data into semantic vector representations that are faithful to original data, compact and editable. The project aims to investigate new bitmap-to-vecto ....Semantic Vectorisation: From Bitmaps to Intelligent Representations. The objective of this innovative project is to provide a solution to the open question of representing natural images by semantically rich vector graphics. The challenges are to identify key visual and temporal elements for images and videos, and efficiently decompose the visual data into semantic vector representations that are faithful to original data, compact and editable. The project aims to investigate new bitmap-to-vector conversion methods. It is expected to develop a framework where semantic labels and hyperlinks can be embedded in visual data automatically. It hopes to pioneer the creation of a web of images where the links are on image/video regions. New image simplification, stylisation, and non-photorealistic rendering methods are expected to be provided.Read moreRead less
The Initiation and 3D Evolution of Instabilities in the Deep Continental Lithosphere. This project is part of a new international initiative in the Geodynamics of the Australian Plate bringing together studies of the active tectonics of the boundary regions of our plate and the ancient analogues of these processes which are locked into the stable interior of the Australian continent. The proposed research is a good fit to the Identification and Extraction of Deep Earth Resources priority goal. D ....The Initiation and 3D Evolution of Instabilities in the Deep Continental Lithosphere. This project is part of a new international initiative in the Geodynamics of the Australian Plate bringing together studies of the active tectonics of the boundary regions of our plate and the ancient analogues of these processes which are locked into the stable interior of the Australian continent. The proposed research is a good fit to the Identification and Extraction of Deep Earth Resources priority goal. Detachment of the lithosphere is associated with fertile mantle being emplaced at shallow depth below the crust; an important precursory event for mineralization. The project builds upon AuScope (NCRIS 5.13) to create infrastructure for a new, smart resource exploration and extraction industry based on modelling and simulation.Read moreRead less
Understanding the deep driving forces of Earth’s large-scale topography through time. We propose to model the convection of Earth’s mantle linked to tectonic plate motions to unravel their combined influence on the evolution of topography over 550 million years. The project will lead to an understanding of the driving forces of large-scale topography in continental interiors and along their margins through geological time.
Nonlinear Signal Processing: Optimisation and Tracking on Manifolds. Most hi-tech electronic devices must process signals. A mobile phone, for example, must encode, transmit, decode and receive voice signals. This project will use specialised mathematical theories applied in novel ways to advance the theoretical foundations of signal processing and develop better signal processing algorithms for practical applications. Companies with access to better signal processing algorithms have an edge ov ....Nonlinear Signal Processing: Optimisation and Tracking on Manifolds. Most hi-tech electronic devices must process signals. A mobile phone, for example, must encode, transmit, decode and receive voice signals. This project will use specialised mathematical theories applied in novel ways to advance the theoretical foundations of signal processing and develop better signal processing algorithms for practical applications. Companies with access to better signal processing algorithms have an edge over their competitors, and consumers benefit too from better and more advanced products.Read moreRead less
Mathematical, logical and computational foundations of hybrid control systems, and their application to design and synthesis problems in control engineering. Hybrid control systems are mathematical models of heterogeneous systems consisting of digital computer components interacting in real-time with continuous physical processes. Their many engineering applications include air traffic control, medical technology and automated transport. Motivated by such safety-critical and high-confidence appl ....Mathematical, logical and computational foundations of hybrid control systems, and their application to design and synthesis problems in control engineering. Hybrid control systems are mathematical models of heterogeneous systems consisting of digital computer components interacting in real-time with continuous physical processes. Their many engineering applications include air traffic control, medical technology and automated transport. Motivated by such safety-critical and high-confidence applications, the project aims to develop a unified framework of mathematical logics adequate to formally represent and reason about the structure, behaviour, and properties of hybrid control systems, and use this to develop methodologies for automatically synthesising hybrid control programs that are provably correct with respect to their specifications. Other outcomes include prototype software implementations of hybrid controller design tools.Read moreRead less
Parametric VR: An Interactive Virtual Reality System for Parametric Design. This project aims to create a new and intuitive set of user interactions for Virtual Reality (VR) to support parametric designers in architecture and design. Parametric tools are an emerging design technology dominating contemporary practices, yet their interfaces are on traditional desktop computers while VR is only employed to visualise the geometric models produced by the end design. This project will generate Paramet ....Parametric VR: An Interactive Virtual Reality System for Parametric Design. This project aims to create a new and intuitive set of user interactions for Virtual Reality (VR) to support parametric designers in architecture and design. Parametric tools are an emerging design technology dominating contemporary practices, yet their interfaces are on traditional desktop computers while VR is only employed to visualise the geometric models produced by the end design. This project will generate Parametric VR, a system of VR tools to support parametric design. Key outcomes include software tools and demonstrators to support parametric algorithms and processes in VR. This will have significant benefits for design industries, allowing designers to directly edit parametric design entirely in VR across the project lifecycle.Read moreRead less