Design automation for secure, reliable and energy efficient embedded processors. This project seeks to create a methodology to design and generate processors which are both secure, reliable and energy efficient for deployment in Internet of Things (IoT) systems, which require little on-going maintenance. In such systems, both security and reliability are paramount, particularly in medical devices, control devices in critical machinery, financial transactions and automotive electronics. The proje ....Design automation for secure, reliable and energy efficient embedded processors. This project seeks to create a methodology to design and generate processors which are both secure, reliable and energy efficient for deployment in Internet of Things (IoT) systems, which require little on-going maintenance. In such systems, both security and reliability are paramount, particularly in medical devices, control devices in critical machinery, financial transactions and automotive electronics. The project will use an open RISC-V processor which is sufficiently flexible to function as a base processor, with a myriad of tools such as compilers and debuggers available. Reliable computing machinery will enable systems to work in hostile environments and be functionally correct for longer.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE220100680
Funder
Australian Research Council
Funding Amount
$403,482.00
Summary
Making Anomaly Detection Interpretable & Actionable in Hostile Environments. Anomaly detection plays a vital role in cyber security to identify threat patterns hidden within large volumes of data. However, current approaches experience high false alarm rates in noisy, heterogeneous and adversarial environments. This project aims to identify and interpret anomalies that can disrupt system performance by introducing the concept of actionable anomalies. It will significantly advance the effectivene ....Making Anomaly Detection Interpretable & Actionable in Hostile Environments. Anomaly detection plays a vital role in cyber security to identify threat patterns hidden within large volumes of data. However, current approaches experience high false alarm rates in noisy, heterogeneous and adversarial environments. This project aims to identify and interpret anomalies that can disrupt system performance by introducing the concept of actionable anomalies. It will significantly advance the effectiveness of anomaly detection by developing algorithms that distil local and global structures of data to characterise actionable anomalies and explain their outlying aspects. Project outcomes will enhance the security, trustworthiness and fault-tolerance of critical systems, contributing to international efforts in cyber security.Read moreRead less