Learning to Pinpoint Emerging Software Vulnerabilities. This project aims to develop learning-based software vulnerability detection techniques to improve the reliability and security of modern software systems. The existing techniques relying on conventional yet rigid software analysis and testing techniques are ineffective and/or inefficient when detecting a wide variety of emerging software vulnerabilities. The outcomes of this project will be a deep-learning-based detection approach and an ....Learning to Pinpoint Emerging Software Vulnerabilities. This project aims to develop learning-based software vulnerability detection techniques to improve the reliability and security of modern software systems. The existing techniques relying on conventional yet rigid software analysis and testing techniques are ineffective and/or inefficient when detecting a wide variety of emerging software vulnerabilities. The outcomes of this project will be a deep-learning-based detection approach and an open-source tool that can capture precision correlations between deep code features and diverse vulnerabilities to pinpoint emerging vulnerabilities without the need for bug specifications. Significant benefits include greatly improved quality, reliability and security for modern software systems.Read moreRead less
Using data mining methods to remove uncertainties in sensor data streams. This project will develop key techniques for removing uncertainties in sensor data streams and thus improve the monitoring quality of sensor networks. The expected outcomes will benefit Australia by enabling improved, lower-cost monitoring of natural resources and management of stock raising.
Deep Data Mining for Anomaly Prediction from Sensor Data Streams. Sensor data streams are crucial for anomaly predictions in real-life monitoring. However, balancing efficiency and accuracy in predicting anomalies with sensor streams is a great challenge; it requires new techniques that go beyond detecting anomalies and predicting trends. This project will develop a deep mining method for anomaly prediction from sensor streams; it will comprise mining algorithms at various levels - from compress ....Deep Data Mining for Anomaly Prediction from Sensor Data Streams. Sensor data streams are crucial for anomaly predictions in real-life monitoring. However, balancing efficiency and accuracy in predicting anomalies with sensor streams is a great challenge; it requires new techniques that go beyond detecting anomalies and predicting trends. This project will develop a deep mining method for anomaly prediction from sensor streams; it will comprise mining algorithms at various levels - from compressing massive raw data, to recognition of abnormal waveforms preceding anomalies, and to retrieving and summarising similar past anomalies for creating descriptions of future anomalies. The project will demonstrate our method in health/environment monitoring applications, and its adoption will save resources, money and lives.Read moreRead less
Deep analytics of non-occurring but important behaviours. This project aims to build a systematic theory for the deep analytics of complex and important occurring and non-occurring behaviours. Behaviours that should occur but do not take place, called non-occurring behaviours (NOB), are widely evident but easily overlooked, such as missed important medical treatments. While often occurring behaviours are focused, such NOB may be associated with significant effects such as a threat to health. Thi ....Deep analytics of non-occurring but important behaviours. This project aims to build a systematic theory for the deep analytics of complex and important occurring and non-occurring behaviours. Behaviours that should occur but do not take place, called non-occurring behaviours (NOB), are widely evident but easily overlooked, such as missed important medical treatments. While often occurring behaviours are focused, such NOB may be associated with significant effects such as a threat to health. This project expects to fill the knowledge gaps in representing, analysing and evaluating NOB complexities and impact, with significant benefits for the evidence-based detection, prediction and risk management of covert NOB applications and their important effects.Read moreRead less
Knowledge discovery from data in the context of prior beliefs. This project will invent user-centric technologies for discovering knowledge from data that are distinguished by taking account of the user's beliefs, enabling more useful discoveries to be made. This project will also invent methods that identify the relative potential value of those discoveries, helping the user derive greater value from their data assets.
Time Series Classification for Complex Dynamic Global Problems. This project aims to increase understanding of complex dynamic processes by creating new ways of analysing large quantities of data collected over time. These new approaches will be specifically designed to greatly improve the understanding obtained from time varying data for trillions of global earth observation data points in an application-agnostic way that is applicable to many tasks. The outcomes are expected to advance the the ....Time Series Classification for Complex Dynamic Global Problems. This project aims to increase understanding of complex dynamic processes by creating new ways of analysing large quantities of data collected over time. These new approaches will be specifically designed to greatly improve the understanding obtained from time varying data for trillions of global earth observation data points in an application-agnostic way that is applicable to many tasks. The outcomes are expected to advance the theory and practice of time-series data analysis and transform the analysis of complex dynamics. This should support innovation in industry, commerce, government and research and magnify benefit from many data investments including the $1 billion Australian governments invest annually in satellite imaging.Read moreRead less
Combining generative and discriminative strategies to facilitate efficient and effective learning from big data. Effective extraction of information from massive data stores is increasingly problematic as data quantities continue to grow rapidly. Quite simply, effective techniques for learning from small data do not scale. However, the problem is even worse than this. Big data contain more information than the small data in which context most state-of-the-art learning algorithms have been develo ....Combining generative and discriminative strategies to facilitate efficient and effective learning from big data. Effective extraction of information from massive data stores is increasingly problematic as data quantities continue to grow rapidly. Quite simply, effective techniques for learning from small data do not scale. However, the problem is even worse than this. Big data contain more information than the small data in which context most state-of-the-art learning algorithms have been developed. For small data overly detailed classifiers will overfit the data and so should be avoided. In contrast, big data provide fine detail and hence will benefit new types of learner that can capture it. This project will deliver learners that are not only capable of capturing this detail, but do so with the efficiency required to process terabytes of data.Read moreRead less
Adversarial Learning of Hybrid Representation. This project aims to design and implement a foundational deep representation learning framework for early detection, classification and defense of emerging malware by capturing their underlying behaviours via structured and unstructured heterogeneous information through hybrid representation learning, behaviour graph mining, and symbolic adversarial learning to discover and defend unknown malware families, thereby significantly boosting the accuracy ....Adversarial Learning of Hybrid Representation. This project aims to design and implement a foundational deep representation learning framework for early detection, classification and defense of emerging malware by capturing their underlying behaviours via structured and unstructured heterogeneous information through hybrid representation learning, behaviour graph mining, and symbolic adversarial learning to discover and defend unknown malware families, thereby significantly boosting the accuracy and robustness of existing classifiers and detectors. The resulting representation learning framework will enhance the national security to protect user privacy, reducing the multi-million-dollar loss caused by fraudulent transactions, and defending against cyber attacks.Read moreRead less
Constraint-based Privacy Preserving BioSignal Data Management on Blockchain. This project aims to address the issue of user privacy in Bio-Signal data analysis by utilizing the capabilities of differential privacy, smart contracts and blockchain technologies. This project expects to generate new knowledge in the area of privacy to develop an advanced privacy-preserving Bio-Signal data analytic framework. The expected outcomes of this project include increased privacy of user data, and the unifi ....Constraint-based Privacy Preserving BioSignal Data Management on Blockchain. This project aims to address the issue of user privacy in Bio-Signal data analysis by utilizing the capabilities of differential privacy, smart contracts and blockchain technologies. This project expects to generate new knowledge in the area of privacy to develop an advanced privacy-preserving Bio-Signal data analytic framework. The expected outcomes of this project include increased privacy of user data, and the unification of standards on human-specific data analysis, saving time and money spent on privacy breaches. This should provide significant benefits in preserving the quality and integrity of the healthcare services provided by the Australian government and private sector.Read moreRead less
Robust Federated Learning for Imperfect Decentralised Data. This project aims to develop a next-generation robust federated learning framework to tackle the challenging scenarios of imperfect decentralised data in real applications, e.g. mobile phones and the Internet of Things (IoT) devices. The outcomes will bring great benefits to a broad range of industry sectors by providing novel large-scale intelligent applications with privacy preservation. The proposed method will advance the developmen ....Robust Federated Learning for Imperfect Decentralised Data. This project aims to develop a next-generation robust federated learning framework to tackle the challenging scenarios of imperfect decentralised data in real applications, e.g. mobile phones and the Internet of Things (IoT) devices. The outcomes will bring great benefits to a broad range of industry sectors by providing novel large-scale intelligent applications with privacy preservation. The proposed method will advance the development of a cutting-edge technique to develop new intelligent applications in a decentralised and privacy-sensitive scenario. This game-changing research will advance current data mining and artificial intelligence research from centralised intelligence to decentralised intelligence with a collaboration network.Read moreRead less