Preventing sensitive data exfiltration from insiders . Confidential data such as military secrets or intellectual property must never be disclosed outside the organisation; formally protecting data exfiltration from insider attacks is a major challenge. This project aims to develop a pattern matching based systematic methodology for data exfiltration in database systems. We will devise highly accurate detection tools and secure provenance techniques that can effectively protect against insider a ....Preventing sensitive data exfiltration from insiders . Confidential data such as military secrets or intellectual property must never be disclosed outside the organisation; formally protecting data exfiltration from insider attacks is a major challenge. This project aims to develop a pattern matching based systematic methodology for data exfiltration in database systems. We will devise highly accurate detection tools and secure provenance techniques that can effectively protect against insider attacks. The outcomes of the project will incorporate new security constraints and policies raised by emerging technologies to enable better protection of sensitive information. Read moreRead less
An active approach to detect and defend against peer-to-peer botnets. The aim of this project is to develop an effective defence system to help organisations detect and defend against the peer-to-peer (P2P) botnets. If this research is accomplished successfully, it will be a big step forward in defeating this new but devastating malicious software widely utilised by Internet criminals and terrorists. The capability of a nation to defend against the P2P botnet attacks on its information infrastru ....An active approach to detect and defend against peer-to-peer botnets. The aim of this project is to develop an effective defence system to help organisations detect and defend against the peer-to-peer (P2P) botnets. If this research is accomplished successfully, it will be a big step forward in defeating this new but devastating malicious software widely utilised by Internet criminals and terrorists. The capability of a nation to defend against the P2P botnet attacks on its information infrastructure is central to the control of such attacks and hence to a nation's long-term survival and prosperity. The outcomes of this project can be directly used in Australian research communities and adopted by industry and government agencies.Read moreRead less
Privacy preserving and data utility in outsourced systems. Making the best tradeoff between data privacy and utility is a vital challenge in privacy-preserving outsourcing environments. This project aims to develop a balanced distributed framework to achieve the best utility of outsourced data while protecting private information. The framework consists of general structure of distributed evolutionary algorithms and a predefined topology for high optimization efficiency and a dynamic groupin ....Privacy preserving and data utility in outsourced systems. Making the best tradeoff between data privacy and utility is a vital challenge in privacy-preserving outsourcing environments. This project aims to develop a balanced distributed framework to achieve the best utility of outsourced data while protecting private information. The framework consists of general structure of distributed evolutionary algorithms and a predefined topology for high optimization efficiency and a dynamic grouping recombination model. The project outcomes will be beneficial to applications in the nation as it incorporates new privacy constraints and utility requirements raised by emerging technologies to enable better protection of sensitive information and maximal data utility in outsourced systems. Read moreRead less
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
Defending AI based FinTech Systems against Model Extraction Attacks. This project aims to develop new methods for defending artificial intelligence (AI) based FinTech systems from highly potent and insidious model extraction attacks whereby an adversary can steal the AI model from the system to cause intellectual property (IP) violation, business advantage disruption, and financial loss. This can be achieved by examining various attack models, creating active and utility-preserving defences, and ....Defending AI based FinTech Systems against Model Extraction Attacks. This project aims to develop new methods for defending artificial intelligence (AI) based FinTech systems from highly potent and insidious model extraction attacks whereby an adversary can steal the AI model from the system to cause intellectual property (IP) violation, business advantage disruption, and financial loss. This can be achieved by examining various attack models, creating active and utility-preserving defences, and inventing non-removable watermarks on AI models. The outcomes are new tools for securing AI-based FinTech systems before deployment and tools for IP violation forensics post-deployment. Such capabilities are beneficial by improving the security and safety of FinTech systems and other nationally critical AI systems.Read moreRead less
Novel audio watermarking techniques for tracing multimedia piracy. This project aims to develop inaudible, high-capacity audio watermarking techniques to trace the illegal copying and distribution of multimedia data containing a sound component, such as audios and sound videos. With the rapid growth of communication networks and the use of advanced multimedia technology, digital multimedia data can be easily copied, manipulated and distributed. This has led to strong demand for new techniques to ....Novel audio watermarking techniques for tracing multimedia piracy. This project aims to develop inaudible, high-capacity audio watermarking techniques to trace the illegal copying and distribution of multimedia data containing a sound component, such as audios and sound videos. With the rapid growth of communication networks and the use of advanced multimedia technology, digital multimedia data can be easily copied, manipulated and distributed. This has led to strong demand for new techniques to prevent illegal use of copyrighted data. The project is expected to advance the theory of audio watermarking and enhance Australia's international competitiveness in this field.
Read moreRead less
A provable privacy-preserving data sharing system for the cloud environment. This project aims to develop an innovative data sharing system, with a mathematically provable privacy guarantee, in a cloud environment. This will be adopted by Australian Education Management Group’s (AEMG) cloud campus to exchange data in a restricted privacy manner between partner institutions. It will be commercialised as a middleware that can be plugged into existing cloud environments to maintain required privacy ....A provable privacy-preserving data sharing system for the cloud environment. This project aims to develop an innovative data sharing system, with a mathematically provable privacy guarantee, in a cloud environment. This will be adopted by Australian Education Management Group’s (AEMG) cloud campus to exchange data in a restricted privacy manner between partner institutions. It will be commercialised as a middleware that can be plugged into existing cloud environments to maintain required privacy even when the cloud crosses various jurisdictions with different privacy policies. The outcomes will benefit educational organisations, and lay the foundations for data sharing in other communities such as the government, banks, and other industries in Australia.Read moreRead less
Privacy-Preserving Fog Info System in Infrastructure-Deficient Environments. Due to Australia’s unique geographical distribution and population density, many regional or remote areas lack infrastructural support and development, including telecommunications and electricity supply. It is important to provide information and communication services in such infrastructure-deficient environments. In this project, we will develop a first-ever commercially ready Fog information system, or FogIS in shor ....Privacy-Preserving Fog Info System in Infrastructure-Deficient Environments. Due to Australia’s unique geographical distribution and population density, many regional or remote areas lack infrastructural support and development, including telecommunications and electricity supply. It is important to provide information and communication services in such infrastructure-deficient environments. In this project, we will develop a first-ever commercially ready Fog information system, or FogIS in short, to enable localised information and communication services, while preserving users' privacy, in infrastructure-deficient environments. The deployment of this system will bring great benefits to Australia’s economic growth, the quality of life, cybersecurity, and environment control in rural and regional Australia. Read moreRead less
Intelligent Technologies for Smart Cryptography. This project aims to improve cybersecurity by automating the process of generating cryptographic software for smart devices. The expected outcomes are tools that automatically produce efficient cryptographic software that resists attacks. The main benefit of this project is to reduce the amount of expert labour required when developing secure software.