Discovery Early Career Researcher Award - Grant ID: DE240100168
Funder
Australian Research Council
Funding Amount
$413,847.00
Summary
Self-Supervised Sequential Biomedical Image-Omics. This project aims to develop a self-supervised sequential biomedical image-omics model to uncover the underlying biological processes e.g., normal or abnormal. Sequential biomedical images are state-of-the-art imaging modalities which allow to depict changes in progression to the human body. New self-supervised machine learning algorithms are proposed to derive features from heterogenous and unlabelled sequential images. These derived features w ....Self-Supervised Sequential Biomedical Image-Omics. This project aims to develop a self-supervised sequential biomedical image-omics model to uncover the underlying biological processes e.g., normal or abnormal. Sequential biomedical images are state-of-the-art imaging modalities which allow to depict changes in progression to the human body. New self-supervised machine learning algorithms are proposed to derive features from heterogenous and unlabelled sequential images. These derived features will then be used to characterise the morphological and functional changes, which provide opportunities to increase understanding of progression of diseases of individual subject. The outcome from this project will provide new insights into system biology with potential future benefits in healthcare.Read moreRead less
Effective software vulnerability detection for web services. This project aims to design and implement new and better methods to find vulnerabilities in software services delivered over the web or through the cloud, as well as methods for proving the absence of certain types of vulnerability. So-called injection attacks are pervasive and generally considered the most important security threat on today's Internet. The programming languages used for software services tend to use strings as a unive ....Effective software vulnerability detection for web services. This project aims to design and implement new and better methods to find vulnerabilities in software services delivered over the web or through the cloud, as well as methods for proving the absence of certain types of vulnerability. So-called injection attacks are pervasive and generally considered the most important security threat on today's Internet. The programming languages used for software services tend to use strings as a universal data structure, which unfortunately makes it hard to separate trusted code from untrusted user-provided data. This project intends to develop novel program analysis tools and string constraint solvers, and employ these tools to support sophisticated automated reasoning about string manipulating software.Read moreRead less
Human interaction with context-aware computing systems. Context-aware systems can provide seamless support of IT applications in a variety of technologies and therefore can improve: (i) work performance and adoption of IT in many industries; and (ii) the quality of life through better support for health services, education, and everyday tasks. Currently proposed solutions for context-aware systems fail to deliver systems which are usable for non-IT professionals. The proposed project will show h ....Human interaction with context-aware computing systems. Context-aware systems can provide seamless support of IT applications in a variety of technologies and therefore can improve: (i) work performance and adoption of IT in many industries; and (ii) the quality of life through better support for health services, education, and everyday tasks. Currently proposed solutions for context-aware systems fail to deliver systems which are usable for non-IT professionals. The proposed project will show how to design context-aware systems that are usable and whose autonomic decisions can be trusted. Additional benefits include increased scientific competitiveness of Australia, strengthened collaboration with international research institutions, and high quality graduates (PhDs, Masters, Honours).Read moreRead less
Linkage Infrastructure, Equipment And Facilities - Grant ID: LE0347131
Funder
Australian Research Council
Funding Amount
$115,490.00
Summary
Intelligent Computer System to Access Information Directly from the Brain Using High Resolution Electroencephalography and Repetitive Transcranial Magnetic Stimulation. The ambitious aim of this project is to create a novel intelligent computer system which accesss information from the brain. To do this we use repetitive Transcranial Magnetic Stimulation and high resolution Electroencephalography.
3D Diffusion Models for Generating and Understanding 3D Scenes. Diffusion models, such as DALL-E2 and Imagen, have achieved remarkable success in generating photorealistic images and hold promise to solve long-standing computer vision problems. However, 3D scene generation remains unexplored. This research project aims to bridge the gap by developing 3D diffusion models capable of generating complete 3D scenes. This will advance our theoretical understanding of diffusion in complex 3D environmen ....3D Diffusion Models for Generating and Understanding 3D Scenes. Diffusion models, such as DALL-E2 and Imagen, have achieved remarkable success in generating photorealistic images and hold promise to solve long-standing computer vision problems. However, 3D scene generation remains unexplored. This research project aims to bridge the gap by developing 3D diffusion models capable of generating complete 3D scenes. This will advance our theoretical understanding of diffusion in complex 3D environments and open up new possibilities for applications in fields such as virtual reality, architecture, and city planning. The proposed 3D diffusion models will also enhance the accuracy of computer vision tasks related to 3D scene understanding, such as object detection, tracking, and semantic segmentation.Read moreRead less
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
Scalable & Accountable Privacy-Preserving Blockchain with Enhanced Security. This project aims to address the scalability and accountability of privacy-preserving blockchain by advancing cryptographic techniques. This project expects to develop scalable protocols for privacy-preserving blockchain while also adding accountability for authority to trace cyber crime activities, which is a missing piece in any state-of-the-art public blockchain system. Expected outcomes of this project include not o ....Scalable & Accountable Privacy-Preserving Blockchain with Enhanced Security. This project aims to address the scalability and accountability of privacy-preserving blockchain by advancing cryptographic techniques. This project expects to develop scalable protocols for privacy-preserving blockchain while also adding accountability for authority to trace cyber crime activities, which is a missing piece in any state-of-the-art public blockchain system. Expected outcomes of this project include not only practical solutions for protecting sensitive data recorded in blockchain but also crucial techniques to make the blockchain accountable for practical applications with enhanced security. This project provides significant benefits, such as building a trusted environment for sensitive transactions in the digital economy.Read moreRead less
Domain-specific visual languages for big data analytics applications. This project aims to invent domain-specific visual languages and support model-driven engineering based infrastructure so domain experts can specify, generate and apply complex data analytics and visualisation techniques. Many domains, including intelligent transport, business intelligence, and population health, need more effective “big data” analytics and visualisation. A challenge is to combine detailed domain knowledge – w ....Domain-specific visual languages for big data analytics applications. This project aims to invent domain-specific visual languages and support model-driven engineering based infrastructure so domain experts can specify, generate and apply complex data analytics and visualisation techniques. Many domains, including intelligent transport, business intelligence, and population health, need more effective “big data” analytics and visualisation. A challenge is to combine detailed domain knowledge – what the data means and what it can be used for – with sophisticated, scalable computational techniques to mine and present information from the huge volumes of raw data. This project is expected to improve productivity and quality of big data analytics and visualisation in critical domains.Read moreRead less
Preventing sensitive data exfiltration from insiders . Confidential data such as military secrets or intellectual property must never be disclosed outside the organisation; formally protecting data exfiltration from insider attacks is a major challenge. This project aims to develop a pattern matching based systematic methodology for data exfiltration in database systems. We will devise highly accurate detection tools and secure provenance techniques that can effectively protect against insider a ....Preventing sensitive data exfiltration from insiders . Confidential data such as military secrets or intellectual property must never be disclosed outside the organisation; formally protecting data exfiltration from insider attacks is a major challenge. This project aims to develop a pattern matching based systematic methodology for data exfiltration in database systems. We will devise highly accurate detection tools and secure provenance techniques that can effectively protect against insider attacks. The outcomes of the project will incorporate new security constraints and policies raised by emerging technologies to enable better protection of sensitive information. Read moreRead less