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
Personalised Privacy-Preserving Network Data Publishing System . Data sharing has become a driving force for many businesses in industrial sectors. This project aims to develop a privacy preserving network data publishing system that can preserve user privacy in a personalised way while maintaining maximal utility of the published data. To make accurate privacy preservation, this project will design novel learning models to derive accurate users’ correlation and their privacy intention, develop ....Personalised Privacy-Preserving Network Data Publishing System . Data sharing has become a driving force for many businesses in industrial sectors. This project aims to develop a privacy preserving network data publishing system that can preserve user privacy in a personalised way while maintaining maximal utility of the published data. To make accurate privacy preservation, this project will design novel learning models to derive accurate users’ correlation and their privacy intention, develop efficient privacy preserving algorithms to deal with static and dynamic network data sharing. The success of this project will benefit many industries and government agencies to reduce users’ privacy breaches, avoid illegal consequences of sharing data, and enhance these service providers’ service quality.Read moreRead less
Ownership-based Alias Analysis for Securing Unsafe Rust Programs. This project aims to develop an ownership-based alias analysis as a complement to Rust's ownership type system for improving Rust's memory safety. This project, therefore, expects to deliver an alias analysis foundation that can provide stronger memory safety guarantees than the state-of-the-art in detecting memory-safety violations and security vulnerabilities in real-world Rust programs that use unsafe language features. The exp ....Ownership-based Alias Analysis for Securing Unsafe Rust Programs. This project aims to develop an ownership-based alias analysis as a complement to Rust's ownership type system for improving Rust's memory safety. This project, therefore, expects to deliver an alias analysis foundation that can provide stronger memory safety guarantees than the state-of-the-art in detecting memory-safety violations and security vulnerabilities in real-world Rust programs that use unsafe language features. The expected outcomes are a deployable ownership-based alias analysis in the Rust compiler and an industrial-strength open-source framework. These outcomes are expected to provide significant benefits in improving software quality and security in Rust, an emerging language that offers both performance and safety.Read moreRead less
Verified concurrent memory management on modern processors. This project aims to formally verify automatic memory managers in the presence of concurrency and the weakly ordered memory of modern processors. A new framework for verifying memory managers, reusable for a wide range of managed programming languages, target hardware, policies, and algorithms will be developed. Expected technical outcomes include improved techniques to ensure trustworthiness of the foundations on which critical softwar ....Verified concurrent memory management on modern processors. This project aims to formally verify automatic memory managers in the presence of concurrency and the weakly ordered memory of modern processors. A new framework for verifying memory managers, reusable for a wide range of managed programming languages, target hardware, policies, and algorithms will be developed. Expected technical outcomes include improved techniques to ensure trustworthiness of the foundations on which critical software infrastructures are built. This will significantly enhance the security of public and private cyber assets, and deliver applications that are more robust and trustworthy, across a range of critical infrastructure such as transportation, communication, energy and defence.Read moreRead less
Tuning parallel applications on software-defined supercomputers. Supercomputers are used by many Australian industries and laboratories to make better products and perform critical predictions, and it is essential that codes operate efficiently. This project aims to assist programmers in identifying performance bottlenecks in their code quickly and easily. The project expects to supersede the current methods, which are often complex and time-consuming, by developing innovative software tools and ....Tuning parallel applications on software-defined supercomputers. Supercomputers are used by many Australian industries and laboratories to make better products and perform critical predictions, and it is essential that codes operate efficiently. This project aims to assist programmers in identifying performance bottlenecks in their code quickly and easily. The project expects to supersede the current methods, which are often complex and time-consuming, by developing innovative software tools and techniques. The expected outcomes include novel software, verified by industry partners in real world case studies, ranging from life sciences to hypersonic transport. This should provide significant benefits, including the capacity for Australian industries to access world-class supercomputing technology.Read moreRead less
Detecting Asynchronous Event-Driven Order Violations in Android Apps. This project aims to develop an event-interleaving analysis for detecting asynchronous event-driven order violations in Android apps. This project therefore expects to deliver a program analysis foundation that can provide stronger security guarantees than the state of the art against advanced exploits that abuse such asynchronous vulnerabilities. The intended outcomes of this project are a new program analysis technology and ....Detecting Asynchronous Event-Driven Order Violations in Android Apps. This project aims to develop an event-interleaving analysis for detecting asynchronous event-driven order violations in Android apps. This project therefore expects to deliver a program analysis foundation that can provide stronger security guarantees than the state of the art against advanced exploits that abuse such asynchronous vulnerabilities. The intended outcomes of this project are a new program analysis technology and an industrial-strength open-source framework that can significantly raise the bar on mobile software quality and security for Android, the dominant smartphone platform accounting a current market share at 87.0% with 2.9 million apps at Google Play in December 2019.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230100477
Funder
Australian Research Council
Funding Amount
$421,554.00
Summary
Advancing Human Perception: Countering Evolving Malicious Fake Visual Data. The aim of this project is to provide new effective and generalisable deepfake detection methods for automatically detecting maliciously manipulated visual data generated by misused artificial intelligence (AI) techniques. It will present innovative computer vision and image processing knowledge and techniques, enabling the developed methods to advance human perception in recognising fake data, enhance cybersecurity, and ....Advancing Human Perception: Countering Evolving Malicious Fake Visual Data. The aim of this project is to provide new effective and generalisable deepfake detection methods for automatically detecting maliciously manipulated visual data generated by misused artificial intelligence (AI) techniques. It will present innovative computer vision and image processing knowledge and techniques, enabling the developed methods to advance human perception in recognising fake data, enhance cybersecurity, and protect privacy in AI applications. The anticipated outcomes should provide significant benefits to a wide range of applications, such as providing timely alerts to the media, government organisations, and the industry about misleading fake visual data, and preventing financial crimes on synthetic identity fraud.Read moreRead less
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
Discovery Early Career Researcher Award - Grant ID: DE240100967
Funder
Australian Research Council
Funding Amount
$366,000.00
Summary
Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected o ....Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected outcomes include new paradigms for algorithm design and evaluation, and establishing the problem as a focus of international research. The key practical benefit would be to accelerate the wider deployment of visual perception in applications such as autonomous vehicles, interactive robotics, and video analysis.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230101058
Funder
Australian Research Council
Funding Amount
$437,254.00
Summary
Glass-box Deep Machine Perception for Trustworthy Artificial Intelligence. Explainability and Transparency are the key values for development and deployment of Artificial Intelligence (AI) in Australia’s AI Ethics Framework for industry and governments. This project aims to build new tools to make the central technology of AI - deep learning - transparent and explainable. Its expected outputs are novel theory-driven algorithms and unconventional foundational blocks for deep learning that will al ....Glass-box Deep Machine Perception for Trustworthy Artificial Intelligence. Explainability and Transparency are the key values for development and deployment of Artificial Intelligence (AI) in Australia’s AI Ethics Framework for industry and governments. This project aims to build new tools to make the central technology of AI - deep learning - transparent and explainable. Its expected outputs are novel theory-driven algorithms and unconventional foundational blocks for deep learning that will allow humans to clearly interpret the reasoning process of this technology, which is currently not possible. It is expected to significantly advance our knowledge in machine intelligence and perception. Due to their fundamental nature, the project outcomes are likely to benefit industry and scientific frontiers alike.Read moreRead less