Discovery Early Career Researcher Award - Grant ID: DE240101049
Funder
Australian Research Council
Funding Amount
$432,485.00
Summary
Modeling the Diffusion of Evolving Rumours in Social Networks. This project aims to model the complex evolution and diffusion process of evolving rumours in social media. This project expects to develop new theories and associated techniques from operational research (adaptive genetic algorithms), mathematics (network theory), and machine learning (generative adversarial networks) to tackle the challenges in this project. This project aims to develop (1) novel models for the evolution of a rumou ....Modeling the Diffusion of Evolving Rumours in Social Networks. This project aims to model the complex evolution and diffusion process of evolving rumours in social media. This project expects to develop new theories and associated techniques from operational research (adaptive genetic algorithms), mathematics (network theory), and machine learning (generative adversarial networks) to tackle the challenges in this project. This project aims to develop (1) novel models for the evolution of a rumour, (2) novel models for the diffusion of an evolving rumour, and (3) techniques for detecting the diffusion sources of the original rumour and its mutations. This not only will constitute a major advancement in the theory and application of rumour study but also lead the decision-makers in debunking rumours.Read moreRead less
Object-based motion estimation for highly efficient streaming video. This project aims to develop motion and shape estimation tools that allow video content to be predicted at any point in time using frame data that is available at other points in time. Applications of this include video coding, frame synthesis for temporal re-sampling. The project expects to develop algorithms for jointly estimating compact motion and shape descriptions of video content. These descriptions will allow quality re ....Object-based motion estimation for highly efficient streaming video. This project aims to develop motion and shape estimation tools that allow video content to be predicted at any point in time using frame data that is available at other points in time. Applications of this include video coding, frame synthesis for temporal re-sampling. The project expects to develop algorithms for jointly estimating compact motion and shape descriptions of video content. These descriptions will allow quality refinement by progressively adding spatial and temporal detail. It is expected that these compact descriptions will lead to significantly more flexible and efficient transmission of video content over modern communications networks.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE180100428
Funder
Australian Research Council
Funding Amount
$378,392.00
Summary
Developing an Arab culture of investigative journalism. This project aims to critically evaluate the extent to which an Arab culture of investigative journalism could be established. Investigative journalism has critical importance to the enhancement of independent media systems, especially in restrictive media environments. Understanding that investigative journalism training and practice should lead to transparent and representative political systems, this project examines whether Western fram ....Developing an Arab culture of investigative journalism. This project aims to critically evaluate the extent to which an Arab culture of investigative journalism could be established. Investigative journalism has critical importance to the enhancement of independent media systems, especially in restrictive media environments. Understanding that investigative journalism training and practice should lead to transparent and representative political systems, this project examines whether Western frameworks are suitable for conceptualising non-Western investigative journalism cultures. It will develop a theoretical model for investigative journalism specific to the Arab world.Read moreRead less
Broadening Choice and Increasing Diversity in Public Schools. Currently, most families are limited to the public school in their catchment area, meaning the area in which they can afford to live. This leads to socio-economically and ethnically homogenous schools and entrenches disadvantage, as well as denying students the crucial life lessons that flow from being part of a diverse student body. This project aims to investigate a model for allocating public school places that integrates catchment ....Broadening Choice and Increasing Diversity in Public Schools. Currently, most families are limited to the public school in their catchment area, meaning the area in which they can afford to live. This leads to socio-economically and ethnically homogenous schools and entrenches disadvantage, as well as denying students the crucial life lessons that flow from being part of a diverse student body. This project aims to investigate a model for allocating public school places that integrates catchment areas. The expected outcome would be a system that gives families a wider choice, enabling them to enrol in out-of-area schools, while ensuring that allocations remain fair, equitable and balanced, and also delivering benefits such as achieving a desired level of diversity in student populations within schoolsRead 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
To map and enhance Australian musical improvisation as a creative industry. The project maps transforming improviser networks in Australian music since 1970, to inform how cultural innovation develops and disseminates. Application of new statistical techniques (temporal network analysis) will combine with in-depth focus groups to show how improvisation excellence depends on a mix of artistic craft, networked collaboration and institutional support. This knowledge will assist music venues and ind ....To map and enhance Australian musical improvisation as a creative industry. The project maps transforming improviser networks in Australian music since 1970, to inform how cultural innovation develops and disseminates. Application of new statistical techniques (temporal network analysis) will combine with in-depth focus groups to show how improvisation excellence depends on a mix of artistic craft, networked collaboration and institutional support. This knowledge will assist music venues and industry in nurturing improvisation as a cultural force and commercial opportunity for export and tourism attraction post Covid-19. The novel method, integrating computational network analysis with qualitative research, will also inform and build capacity for future understandings of cultural fields and industries.Read moreRead less
Data-driven Approach to Resilient Online Service Systems. This project aims to develop a data-driven approach to improving the resilience of online service systems. Many software systems are now provided as online services via the Internet on a 24/7 basis. Although a lot of effort has been devoted to service quality assurance, in reality, online service systems still encounter many incidents and fail to satisfy user requests. This project expects to develop innovative data-driven methods for eff ....Data-driven Approach to Resilient Online Service Systems. This project aims to develop a data-driven approach to improving the resilience of online service systems. Many software systems are now provided as online services via the Internet on a 24/7 basis. Although a lot of effort has been devoted to service quality assurance, in reality, online service systems still encounter many incidents and fail to satisfy user requests. This project expects to develop innovative data-driven methods for effective fault identification, fault localization, and failure prediction. Expected outcomes of this project include novel techniques and tools for maintaining online service systems. This project will provide significant benefits, such as improving the resilience and reliability of our cyber infrastructure.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230100116
Funder
Australian Research Council
Funding Amount
$419,218.00
Summary
Vulnerability Defence: From Interpretable to Trustworthy Threat Assessment. This project aims to design a novel vulnerability defence framework to automatically identify, prioritise and interpret vulnerabilities and their attack vectors from the Internet of Things (IoT). Currently, most Australian organisations can be targeted by complex cyberattacks, stealing sensitive information leading to financial loss and reputation threats. This project expects to generate new knowledge in IoT vulnerabili ....Vulnerability Defence: From Interpretable to Trustworthy Threat Assessment. This project aims to design a novel vulnerability defence framework to automatically identify, prioritise and interpret vulnerabilities and their attack vectors from the Internet of Things (IoT). Currently, most Australian organisations can be targeted by complex cyberattacks, stealing sensitive information leading to financial loss and reputation threats. This project expects to generate new knowledge in IoT vulnerability assessment using economic risk estimation and cognitive vulnerability identification methods. Expected outcomes include trusted IoT vulnerability assessment methods and vulnerability testbed. Significant benefits are expected to protect IoT networks in all defence, industry and government sectors.Read moreRead less
Testing strategy-proofness in matching markets: an experimental study. This project seeks to test and improve matching algorithms by investigating the effect of advice on strategy-proofness. Matching algorithms are used to solve allocation problems in designed markets (eg school or house allocation problems). Many of the algorithms employed are strategy-proof: participants never gain from strategising, that is, from lying about their preferences. Strategy-proofness had been seemingly validated b ....Testing strategy-proofness in matching markets: an experimental study. This project seeks to test and improve matching algorithms by investigating the effect of advice on strategy-proofness. Matching algorithms are used to solve allocation problems in designed markets (eg school or house allocation problems). Many of the algorithms employed are strategy-proof: participants never gain from strategising, that is, from lying about their preferences. Strategy-proofness had been seemingly validated by experimental research, but new evidence suggests that participants could be prone to follow wrong advice and therefore lie. In order to improve the performance of designed markets, the project proposes to further test strategy-proofness by investigating how advice can affect truth-telling in strategy-proof algorithms and whether learning can counteract or complement the effect of advice.Read moreRead less
Australian Experiences of Algorithmic Culture on TikTok. This project is the first to systematically investigate how algorithmic content recommendation is shaping everyday Australian cultural experience over time, in the particular context of TikTok—the digital platform where Australians spend the most time online. The project provides critical evidence to support the government's ongoing policy initiatives intended to regulate the activities of digital platforms. Its methodological innovations ....Australian Experiences of Algorithmic Culture on TikTok. This project is the first to systematically investigate how algorithmic content recommendation is shaping everyday Australian cultural experience over time, in the particular context of TikTok—the digital platform where Australians spend the most time online. The project provides critical evidence to support the government's ongoing policy initiatives intended to regulate the activities of digital platforms. Its methodological innovations directly address the challenges of studying commercial platforms' recommender systems through a mixed-method research design combining computational and qualitative analysis, bridging universal and individual perspectives and introducing ‘citizen science’ approaches to the field of platform studies.Read moreRead less