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
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
Electrical properties of human dendrites. This project aims to determine the electrical properties of dendrites in human neurons. Dendrites are the primary site of synaptic input to neurons and their electrical properties play a key role in information processing in the brain. While we know much about the electrical properties of dendrites in other species, primarily rodents, little is known about the electrical properties of human dendrites. This project aims to address this gap in knowledge fo ....Electrical properties of human dendrites. This project aims to determine the electrical properties of dendrites in human neurons. Dendrites are the primary site of synaptic input to neurons and their electrical properties play a key role in information processing in the brain. While we know much about the electrical properties of dendrites in other species, primarily rodents, little is known about the electrical properties of human dendrites. This project aims to address this gap in knowledge for the first time. The results obtained will shed light on the mechanisms the brain uses to process information, and therefore will bring us a step closer to truly understanding ourselves.Read moreRead less
Privacy-preserving data processing on the cloud. This project aims to address the current lack of privacy of user data processed by common cloud computing web servers, including email, business data, and confidential files. This project aims to develop new techniques in cryptography. The anticipated outcome is a suite of practical tools enabling common cloud computing processing operations such as search, statistical analysis, and multi-user access control, to be performed efficiently while pres ....Privacy-preserving data processing on the cloud. This project aims to address the current lack of privacy of user data processed by common cloud computing web servers, including email, business data, and confidential files. This project aims to develop new techniques in cryptography. The anticipated outcome is a suite of practical tools enabling common cloud computing processing operations such as search, statistical analysis, and multi-user access control, to be performed efficiently while preserving the data privacy. These tools should provide significant benefits to the privacy of cloud users, as well as financial and reputation benefits to the IT industry, by significantly reducing the likelihood of massive user data privacy breaches in the event of a cyber-hacking attack on the cloud server.Read moreRead less
Role of the superior colliculus in sensory processing. The ability of an organism to attend to, and orient towards, stimuli in the environment is critical for survival. In the mammalian brain, the principal brain region performing this function is the superior colliculus. Despite its importance, little is known about the role the superior colliculus plays in sensory perception. This project addresses this issue by leveraging revolutionary new recording techniques to determine how the superior co ....Role of the superior colliculus in sensory processing. The ability of an organism to attend to, and orient towards, stimuli in the environment is critical for survival. In the mammalian brain, the principal brain region performing this function is the superior colliculus. Despite its importance, little is known about the role the superior colliculus plays in sensory perception. This project addresses this issue by leveraging revolutionary new recording techniques to determine how the superior colliculus codes sensory information and ultimately drives behaviour. The outcomes will be of immediate benefit to scientists studying sensory processing and perceptual decision making, and will help keep Australia at the forefront of brain-inspired engineering and the neuroscience-based knowledge economy.Read moreRead less
The impact of environmental toxicants on the fertility of female animals. This study aims to address a problem of national significance; determining the impact of commonly used environmental toxicants (pesticides) on the fertility and health of female animals, both agricultural and native. This project expects to generate new knowledge in the fields of ovarian biology, female fertility and toxicology by using a combination of mouse and marsupial animal models. The expected outcomes include the e ....The impact of environmental toxicants on the fertility of female animals. This study aims to address a problem of national significance; determining the impact of commonly used environmental toxicants (pesticides) on the fertility and health of female animals, both agricultural and native. This project expects to generate new knowledge in the fields of ovarian biology, female fertility and toxicology by using a combination of mouse and marsupial animal models. The expected outcomes include the establishment of interdisciplinary collaborations and provision of world-class training for staff and students in the field of reproductive biology. This project should provide significant benefits, such as improved chemical management in livestock production and the development of marsupial conservation action plans.Read moreRead less
Modelling human brain development with stem cells and biomaterials. With limited resources to directly study and advance our understanding of human neural development, this
proposal will establish models of 4 key stages. Employing innovative, interdisciplinary approaches, biomaterials will be fabricated to provide structural and chemical support for human stem cells during: (i) neural induction, (ii) specification into neuronal progenitor subpopulations, (iii) neuronal maturation and integration ....Modelling human brain development with stem cells and biomaterials. With limited resources to directly study and advance our understanding of human neural development, this
proposal will establish models of 4 key stages. Employing innovative, interdisciplinary approaches, biomaterials will be fabricated to provide structural and chemical support for human stem cells during: (i) neural induction, (ii) specification into neuronal progenitor subpopulations, (iii) neuronal maturation and integration into complex neural networks as well as, (iv) the organisation of neurons into larger 3-dimensional brain structures, namely folding of the human cortex. Further, biomaterials developed here have commercialisation potential, targeted at standardizing the culturing of human stem cells to defined neural populations.
Read moreRead less
Provable elimination of information leakage through timing channels. This project aims to develop techniques to solve the issue in information security of unauthorised information flow resulting from competition for shared hardware resources. The project will combine operating systems design, formal hardware models, information-flow reasoning and theorem proving to achieve a goal that is widely considered infeasible. The project is expected to result in a system that prevents leakage of critical ....Provable elimination of information leakage through timing channels. This project aims to develop techniques to solve the issue in information security of unauthorised information flow resulting from competition for shared hardware resources. The project will combine operating systems design, formal hardware models, information-flow reasoning and theorem proving to achieve a goal that is widely considered infeasible. The project is expected to result in a system that prevents leakage of critical information, such as encryption keys, through timing channels. This should prevent sophisticated attacks on public clouds, mobile devices and military-grade cross-domain devices.Read moreRead less
Engineering a technology platform for organoids. Protein delivery technologies hold great potential to improve organoids (miniature organs used as in vitro models), allowing a deep understanding of development. However, current limitations must be overcome - particularly cost, precision, and efficacy. This project will engineer delivery materials to improve the efficacy of organoids, allowing control over the location and timing of protein delivery. Outcomes will include a technology platform o ....Engineering a technology platform for organoids. Protein delivery technologies hold great potential to improve organoids (miniature organs used as in vitro models), allowing a deep understanding of development. However, current limitations must be overcome - particularly cost, precision, and efficacy. This project will engineer delivery materials to improve the efficacy of organoids, allowing control over the location and timing of protein delivery. Outcomes will include a technology platform of immediate use in the agriculture sector and for animal model alternatives. The benefit will be widespread, ensuring the growth and sustainability of our health and agriculture sector. The project will increase public understanding of protein delivery technologies, aiding in technology adoption.Read moreRead less