Discovery Early Career Researcher Award - Grant ID: DE210100019
Funder
Australian Research Council
Funding Amount
$408,000.00
Summary
A Scalable and Adaptive-Resilient Blockchain. This project aims to address the security and scalability challenges that limit blockchain adoption. Existing blockchains do not scale and are vulnerable to attacks (e.g. with a total loss of over US$1 billion in 2019). This project expects to improve security by adaptively enforcing the currently broken security assumptions, and to improve scalability by designing blockchains with high concurrency via relaxed criteria on the ordering of transactions ....A Scalable and Adaptive-Resilient Blockchain. This project aims to address the security and scalability challenges that limit blockchain adoption. Existing blockchains do not scale and are vulnerable to attacks (e.g. with a total loss of over US$1 billion in 2019). This project expects to improve security by adaptively enforcing the currently broken security assumptions, and to improve scalability by designing blockchains with high concurrency via relaxed criteria on the ordering of transactions. The expected outcomes include foundations and practical solutions for self-adaptive, secure and scalable blockchains. The benefits of this would be improved confidence in and capacity for building blockchain applications, which have a predicted value of over US$3.1 trillion by 2030.Read moreRead less
Towards full lifecycle privacy protection on cloud. Privacy protection in user data on cloud is now at risk throughout all stages of user information lifecycle facing significant challenges such as stage adaptive protection, across-system protection, privacy invasion tracing and prediction. Current approaches mainly focus on a specific case at certain stage, hence cannot address those challenges properly by considering all stages. This project aims to systematically investigate those challenges ....Towards full lifecycle privacy protection on cloud. Privacy protection in user data on cloud is now at risk throughout all stages of user information lifecycle facing significant challenges such as stage adaptive protection, across-system protection, privacy invasion tracing and prediction. Current approaches mainly focus on a specific case at certain stage, hence cannot address those challenges properly by considering all stages. This project aims to systematically investigate those challenges and expects to establish innovative research and solutions for enabling full lifecycle privacy protection on cloud. The project outcomes will help to safeguard Australian community in fast-growing online cyber world, and benefit to fast-growing privacy sensitive data hosting and applications on cloud.Read moreRead less
Privacy-preserving online user matching. This project aims to develop efficient techniques to preserve the privacy of users of online matching websites used for finding employment, friends and partners. The project expects to generate new knowledge in privacy preserving user matching with multiple servers. The expected outcomes are new techniques that can find matching users without revealing their interests to the matching server and a prototype based on these techniques. This should alleviate ....Privacy-preserving online user matching. This project aims to develop efficient techniques to preserve the privacy of users of online matching websites used for finding employment, friends and partners. The project expects to generate new knowledge in privacy preserving user matching with multiple servers. The expected outcomes are new techniques that can find matching users without revealing their interests to the matching server and a prototype based on these techniques. This should alleviate the privacy concerns of people using online tools that require providing personal information.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
Enhancing information credibility using mathematical prediction. The aim of this project is to develop theory, techniques, mathematical tools and practical algorithms for rumor detection and forecast in social media to enhance credibility of news, especially in time-sensitive situations and trending events. This project will significantly advance human knowledge of rumor formation, detection, and forecast, which will enable timely and efficient counter attacks. The outcomes from this project wil ....Enhancing information credibility using mathematical prediction. The aim of this project is to develop theory, techniques, mathematical tools and practical algorithms for rumor detection and forecast in social media to enhance credibility of news, especially in time-sensitive situations and trending events. This project will significantly advance human knowledge of rumor formation, detection, and forecast, which will enable timely and efficient counter attacks. The outcomes from this project will offer a reliable information environment for our society.Read moreRead less
Private searching on streaming data. This project aims to explore secure and practical solutions for various internet search types and to develop a prototype of a private searching system to avoid compromising user privacy whilst sharing query requests. Searching of streaming data allows collection of useful information from huge streaming sources of data such as on-line news feeds and internet chat-rooms. Current solutions for this problem are inefficient and restricted to a couple of simple se ....Private searching on streaming data. This project aims to explore secure and practical solutions for various internet search types and to develop a prototype of a private searching system to avoid compromising user privacy whilst sharing query requests. Searching of streaming data allows collection of useful information from huge streaming sources of data such as on-line news feeds and internet chat-rooms. Current solutions for this problem are inefficient and restricted to a couple of simple search types, and vulnerable to identifying the search requester. The project expects to develop private searching tools to protect the privacy of user's search queries. This will have the potential to detect any attacks to our digital infrastructure while keeping the search criteria classified, and could have applications in Australian counter-terrorism and homeland defence.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
Discovery Early Career Researcher Award - Grant ID: DE200100016
Funder
Australian Research Council
Funding Amount
$351,798.00
Summary
Enabling Compatible and Secure Mobile Apps via Automated Program Repair. This project aims to ensure everyone in Australia and the world can reliably utilise compatible and secure mobile apps on their smart devices, by inventing a novel approach to automatically fix compatibility and security issues during app development and installation. The project expects to generate new knowledge, tools and methods to support efficient mobile app fix through mining the best practices from the mobile ecosyst ....Enabling Compatible and Secure Mobile Apps via Automated Program Repair. This project aims to ensure everyone in Australia and the world can reliably utilise compatible and secure mobile apps on their smart devices, by inventing a novel approach to automatically fix compatibility and security issues during app development and installation. The project expects to generate new knowledge, tools and methods to support efficient mobile app fix through mining the best practices from the mobile ecosystem. Expected outcomes include better support for app developers to build mobile apps that will maximise the potential of the mobile ecosystem for Australian businesses. This should provide significant benefits, such as enhanced productivity for the software industry and better mobile app experience and safety for users.Read moreRead less
Privacy-aware Smart Access Control for Internet-of-Things on Blockchain. This project aims to address privacy and trust issues in Internet-of-Things (IoT) access control mechanism of smart critical infrastructure. This project expects to generate new knowledge in the area of IoT access control by leveraging privacy-preserving techniques, blockchain, and machine learning. Expected outcomes of this project include enhanced capability to build improved techniques for privacy aware tamperproof IoT a ....Privacy-aware Smart Access Control for Internet-of-Things on Blockchain. This project aims to address privacy and trust issues in Internet-of-Things (IoT) access control mechanism of smart critical infrastructure. This project expects to generate new knowledge in the area of IoT access control by leveraging privacy-preserving techniques, blockchain, and machine learning. Expected outcomes of this project include enhanced capability to build improved techniques for privacy aware tamperproof IoT access control with machine learning based anomaly detection. This should provide significant benefits, such as preventing cyber threats on security and privacy of IoT and improving trust in IoT-enabled smart critical infrastructure of Australia.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