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
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
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE0775582
Funder
Australian Research Council
Funding Amount
$530,000.00
Summary
Data Grid -- Access Layer. Vast increases in computing power and the arrival of new scientific instruments are contributing to the so-called data deluge of the 21st century. Accessing and archiving these data is essential to research. While the underlying computing and network requirements are well resourced, data access has been relatively neglected in Australia. A continuing problem in Australian research communities is the absence of coordinated access to digital storage resources. In many ca ....Data Grid -- Access Layer. Vast increases in computing power and the arrival of new scientific instruments are contributing to the so-called data deluge of the 21st century. Accessing and archiving these data is essential to research. While the underlying computing and network requirements are well resourced, data access has been relatively neglected in Australia. A continuing problem in Australian research communities is the absence of coordinated access to digital storage resources. In many cases computational and experimental data are stored on ad-hoc resources, such as local university servers, PC disc drives, and are not generally accessible. The central goal of this proposal is to provide access to an integrated scientific data storage capacity for Australia.Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE0668445
Funder
Australian Research Council
Funding Amount
$800,000.00
Summary
Data Grid Storage Infrastructure for e-Research. Vast increases in computing power and the arrival of new scientific instruments are contributing to the so-called data deluge of the 21st century. Archiving these data is essential to research. While the underlying computing and network requirements are well resourced, data storage capacity has been relatively neglected in Australia. A continuing problem in Australian research communities is the absence of coordinated digital storage resources. In ....Data Grid Storage Infrastructure for e-Research. Vast increases in computing power and the arrival of new scientific instruments are contributing to the so-called data deluge of the 21st century. Archiving these data is essential to research. While the underlying computing and network requirements are well resourced, data storage capacity has been relatively neglected in Australia. A continuing problem in Australian research communities is the absence of coordinated digital storage resources. In many cases computational and experimental data are stored on ad-hoc resources, such as local university servers, PC disc drives, CDs, or DVDs, and are not generally accessible. The central goal of this proposal is to provide a long-term, integrated scientific data storage capacity for Australia. 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
Reducing The Greatest Uncertainty In Radiotherapy.
Funder
National Health and Medical Research Council
Funding Amount
$594,197.00
Summary
The weakest link in radiotherapy is defining treatment volumes (contouring). Lack of accuracy and consistency in clinical trial contouring has been shown to result in reduced patient outcomes. Manual review of contouring is resource intensive, expensive and for advanced treatments unachievable in a timely fashion. We will assess an automated approach to contouring assessment using 4 clinical trial datasets, changing practice for future studies and enabling consistent assessment in the clinic.
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE160100090
Funder
Australian Research Council
Funding Amount
$250,000.00
Summary
Computational infrastructure for developing deep machine learning models. Computational infrastructure for developing deep machine learning models:
The computational infrastructure for developing deep machine learning models aims to enable new developments in machine learning of deep neural network models by providing the specialised computing necessary to train and evaluate the networks. In the last three years, deep networks have smashed previous performance ceilings for tasks such as object ....Computational infrastructure for developing deep machine learning models. Computational infrastructure for developing deep machine learning models:
The computational infrastructure for developing deep machine learning models aims to enable new developments in machine learning of deep neural network models by providing the specialised computing necessary to train and evaluate the networks. In the last three years, deep networks have smashed previous performance ceilings for tasks such as object recognition in images, speech recognition and automatic translation, bringing the prospect of machine intelligence closer than ever. Modern machine learning techniques have had huge impact in the last decade in fields such as robotics, computer vision and data analytics. The facility would enable Australian researchers to develop, learn and apply deep networks to problems of national importance in robotic vision and big data analytics. Read moreRead less
DNA methylation in insect social evolution. This project will investigate the evolutionary relationship between DNA methylation and the advanced sociality displayed by bees, ants and wasps. The project will map DNA methylation across the social insects and test whether it has coevolved with sociality. It will also determine how a vital social cue, the queen pheromone, influences the worker methylome. Finally, it will apply quantitative genetic and methylomic methods to wild insects, revealing pa ....DNA methylation in insect social evolution. This project will investigate the evolutionary relationship between DNA methylation and the advanced sociality displayed by bees, ants and wasps. The project will map DNA methylation across the social insects and test whether it has coevolved with sociality. It will also determine how a vital social cue, the queen pheromone, influences the worker methylome. Finally, it will apply quantitative genetic and methylomic methods to wild insects, revealing patterns of selection and inheritance in epigenetic and phenotypic traits. By combining genomic and evolutionary methods, the project will advance the ongoing debate about the importance of methylation to sociality and extreme phenotypic plasticity. It will contribute to a quantum leap in our understanding of DNA methylation and sociobiology and mark the first application of quantitative genetics to wild insects.Read moreRead less