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
DeepHoney: Automatic Honey Data Generation for Active Cyber Defence . This project aims to enhance the security of networks and information systems by empowering them with intelligent deception techniques to achieve proactive attack detection and defence. In recent times, the fictitious environment – honeypot designed by human experience becomes popular to attract attackers and capture their interactions. However, rules-based construction of honeypots fails in preserving the privacy, boosting th ....DeepHoney: Automatic Honey Data Generation for Active Cyber Defence . This project aims to enhance the security of networks and information systems by empowering them with intelligent deception techniques to achieve proactive attack detection and defence. In recent times, the fictitious environment – honeypot designed by human experience becomes popular to attract attackers and capture their interactions. However, rules-based construction of honeypots fails in preserving the privacy, boosting the attractiveness and evolving the system. The project expects to advance deep learning and yield novel DeepHoney technologies with associated publications and open-source software. This should benefit science, society, and the economy by building the next generation of active cyber defence systems. Read moreRead less
Energy big data analytics from a cybersecurity perspective. This project aims to develop a framework on energy big data analytics from security and privacy perspectives. Unlike other big data analytics such as social network big data analytics, energy big data analytics involve research challenges on how to cope with real-time tight cyber-physical couplings, and security/safety of the smart grid system. This project will develop advanced data-driven algorithms that are capable of detecting coord ....Energy big data analytics from a cybersecurity perspective. This project aims to develop a framework on energy big data analytics from security and privacy perspectives. Unlike other big data analytics such as social network big data analytics, energy big data analytics involve research challenges on how to cope with real-time tight cyber-physical couplings, and security/safety of the smart grid system. This project will develop advanced data-driven algorithms that are capable of detecting coordinated cyber-attacks that will potentially lead to catastrophic cascaded failures; and develop new solutions in detecting the false data-injection attacks that are conventionally considered as unobservable. This project will provide the benefit of enhancing our national critical infrastructure's security.Read moreRead less
The growth of giant black holes in the early universe. This project aims to discover the largest black holes in the early universe and their origin, and weigh them using infrared spectroscopy. Giant black holes at the centres of galaxies reach masses over ten billion times that of our Sun. Astronomy has revealed the origin of black holes with masses similar to that of the Sun, but remains puzzled by the existence of those with masses many million times larger. This project will reveal pathways o ....The growth of giant black holes in the early universe. This project aims to discover the largest black holes in the early universe and their origin, and weigh them using infrared spectroscopy. Giant black holes at the centres of galaxies reach masses over ten billion times that of our Sun. Astronomy has revealed the origin of black holes with masses similar to that of the Sun, but remains puzzled by the existence of those with masses many million times larger. This project will reveal pathways of black-hole growth early after the Big Bang. The project will shed light on the evolution of galaxies in the early universe and prepare the ground for new work by other scientists, for example on the origin of the elements.Read moreRead less
Privacy-preserving Biometrics based Authentication and Security. Password based authentication systems cannot verify genuine users. Biometric authentication can address this issue. However, the booming IoT applications and cloud computing require that the biometric authentication must be conducted in the privacy-protected setting in order to comply with privacy protection legal regulations. Latest reports show that current biometric authentication systems, under protected setting, exhibit poor ....Privacy-preserving Biometrics based Authentication and Security. Password based authentication systems cannot verify genuine users. Biometric authentication can address this issue. However, the booming IoT applications and cloud computing require that the biometric authentication must be conducted in the privacy-protected setting in order to comply with privacy protection legal regulations. Latest reports show that current biometric authentication systems, under protected setting, exhibit poor authentication performance, which is not commercially applicable. This project aims to investigate innovative solutions to this issue. The intended deliverables will include deep learning based biometric feature extractor, cancellable biometrics and cloud oriented biometrics security protocols. Read moreRead less
Improving the specificity of affective computing via multimodal analysis. This project aims to develop multimodal affective sensing techniques that can sense very subtle expressions in human moods and emotions. Much research in affective computing has investigated ways to improve the sensitivity of affect sensing approaches, resulting in more accurate estimates of affective states such as emotions or mood. What remains unsolved so far is the issue of specificity. This project will address this i ....Improving the specificity of affective computing via multimodal analysis. This project aims to develop multimodal affective sensing techniques that can sense very subtle expressions in human moods and emotions. Much research in affective computing has investigated ways to improve the sensitivity of affect sensing approaches, resulting in more accurate estimates of affective states such as emotions or mood. What remains unsolved so far is the issue of specificity. This project will address this issue through novel analyses of very subtle cues in facial and vocal expressions of affect embedded in a multimodal deep learning framework. Current approaches can successfully assist in binary classification tasks. This project will tackle the much more difficult problem of developing advanced affective sensing technology to simultaneously handle homogeneous and heterogeneous affect classes as well as continuous range estimates of affect intensity.Read moreRead less
Deep Learning for Graph Isomorphism: Theories and Applications. This project aims to investigate graph isomorphism, a fundamental problem in graph theory, using deep learning techniques. Solutions to graph isomorphism are in demand by researchers in many fields of science, such as biology, chemistry, computer science, and quantum computing. The project expects to advance knowledge about graph isomorphism and state-of-the-art methodologies for its applications. The expected outcomes include new t ....Deep Learning for Graph Isomorphism: Theories and Applications. This project aims to investigate graph isomorphism, a fundamental problem in graph theory, using deep learning techniques. Solutions to graph isomorphism are in demand by researchers in many fields of science, such as biology, chemistry, computer science, and quantum computing. The project expects to advance knowledge about graph isomorphism and state-of-the-art methodologies for its applications. The expected outcomes include new theoretical insights on combinatorial structures of graphs, efficient heuristic techniques for (maximum) subgraph isomorphism, and structured representation learning. The project should provide significant benefits to research in a wide range of science fields, as well as many real-world applications.Read moreRead less
Personalised Learning for Per-pixel Prediction Tasks in Image Analysis. AI-assisted image segmentation & synthesis are very challenging and usually require pixel-level labelling (per-pixel prediction) that is costly to obtain. The small amount of labels makes it difficult to train an “optimal” unified model for varied data as conventional methods did. This project aims to develop a new paradigm “personalised learning” to tackle this problem, where each image could be dealt with a model tailored ....Personalised Learning for Per-pixel Prediction Tasks in Image Analysis. AI-assisted image segmentation & synthesis are very challenging and usually require pixel-level labelling (per-pixel prediction) that is costly to obtain. The small amount of labels makes it difficult to train an “optimal” unified model for varied data as conventional methods did. This project aims to develop a new paradigm “personalised learning” to tackle this problem, where each image could be dealt with a model tailored to individual characteristics. The success of this project could significantly advance the fundamental research in image analysis. Expected outcomes include new knowledge and algorithms for image analysis, which could benefit fields like biology and archaeology, where labeled images are hard to attain and scarce.Read moreRead less
Quantum-Inspired Machine Learning. This project aims to develop new machine learning techniques based around the close correspondence between
neural networks used in deep learning, and tensor networks used in quantum physics. Tensor networks are a form of information compression that is useful in machine learning to construct a compact representation of a large data set in a way that is more amenable to understanding the internal structure than a deep neural network. Expected outcomes of this pr ....Quantum-Inspired Machine Learning. This project aims to develop new machine learning techniques based around the close correspondence between
neural networks used in deep learning, and tensor networks used in quantum physics. Tensor networks are a form of information compression that is useful in machine learning to construct a compact representation of a large data set in a way that is more amenable to understanding the internal structure than a deep neural network. Expected outcomes of this project include more resilient algorithms for machine learning, and new ways to represent quantum states that will impact fundamental physics. The resulting benefits include enhanced capacity for cross-discipline collaboration, and improved methods for future industrial applications.
Read moreRead less
Uncertainty, Risk and Related Concepts in Machine Learning. Machine learning is the science of making sense of data. It does not and cannot remove all risk and uncertainty. This project proposes to study the foundations of how machine learning uses, represents and communicates risk and uncertainty. It aims to do so by finding new theoretical connections between diverse notions that have arisen in allied disciplines. These include risk, uncertainty, scoring rules and loss functions, divergences, ....Uncertainty, Risk and Related Concepts in Machine Learning. Machine learning is the science of making sense of data. It does not and cannot remove all risk and uncertainty. This project proposes to study the foundations of how machine learning uses, represents and communicates risk and uncertainty. It aims to do so by finding new theoretical connections between diverse notions that have arisen in allied disciplines. These include risk, uncertainty, scoring rules and loss functions, divergences, statistics and different ways of aggregating information. By building a more complete theoretical map it is expected that new machine learning methods will be developed, but more importantly that machine learning will be able to be better integrated into larger socio-technical systems.Read moreRead less