Past Industry Co-Funded Projects

The aim of this project was to develop a video-enhanced case study and associated teaching materials that addresses the learning objectives of the Holmes Institute’s cyber security education program.

Project Goal:

The project was innovative in that it explained how storytelling could be used to improve cyber security education. Research in case-based teaching had been limited by the lack of creativity and relied on laborious text-based case studies in developing innovative approaches to delivering training and education. This project advanced knowledge by engaging in:

1. the application of storytelling to tertiary education; and
2. the application of learning principles and methods in the design and development of fictional storytelling for dramatization purposes.

You can watch the trailers on our YouTube channel.

‘HealthEngine’ is an existing app which is widely used in medical centres in Victoria Australia. The app allows customers and patients to book medical appointments by themselves online. By clicking the booking URL, the available slots of each individual practitioners are shown.

The app has functionality however the inline security, scheduling and delay notification are missed which has resulted in vulnerabilities such as ‘eavesdropper and hackers’ due to the lack of security protection for the message users input and transmission, infringement of user privacy and inefficient or user-friendly interaction.

Project Goal:

The goal of this project is to develop a portable online booking management protocol which is secure and provides better user interaction. A set of apps for the proof-of-concept will be developed, focusing on:

The ‘Spam email categorization using natural language processing and attention-embedded deep learning’ project is a three-way partnership between Federation University, La Trobe University and Westpac.

Federation University is responsible for coordinating and delivering the project using its in-house capabilities in AI, natural language processing, cyber security, knowledge, and experience of banking industry cyber threats to deliver tools to triage cyberattacks.

Westpac Bank is providing datasets and the know-how of the operating environment of the developed tools and Latrobe University is lending its expertise in determining the signatures of the cyber-attacks in a simulated sandboxed environment.

Project Goal:

This proposal aims at tackling the spam email problem from a multidimensional perspective. The objective of the proposal is to classify emails into scams, malware, spam, phishing, and other categories.

In this research, we will propose and evaluate a novel method consisting of feature extraction and innovative machine learning technique to classify spam emails.

The feature extraction and selection technique will include natural language processing techniques to reveal the distinct inherent structural characteristics that are commonly present in the emails of various categories.

Machine learning techniques will explore and enhance the capability of the newly proposed neural networks based on attention mechanism.

The outcome of this project will provide customers with increased protection from financial fraud resulting from email-based malware as well as aid the banking industry to strengthen their security further and gain enhanced customer trust by stopping such attacks.

This project designed and implemented an encrypted and distributed NoSQL (referring to “non SQL” or “non relational”) data storage system. The system aimed to allow data to be stored in encrypted forms and servers to process encrypted rich queries efficiently over encrypted data, and build and deploy the prototype based on the off-the-shelf NoSQL data stores (e.g., Redis and RocksDB) with minimum modifications at their underlying architecture while achieving strong security guarantees.

Project Goal:

The project goals were to design and build system architecture tailored for the encrypted and distributed data stores, that would integrate the data partition algorithm to evenly distribute the encrypted data to a cluster of servers and realise an encrypted index framework which would facilitate query processing over encrypted data in parallel.

Another aim was to develop and deploy two cryptographic primitives, i.e., searchable symmetric encryption (SSE) and order-revealing encryption (ORE) to the system, so as to enable exact-match and range-match based queries, respectively and provide a package of API’s systems  and APIs to support queries via primary keys or via secondary attributes of data, that are currently enabled in most plaintext NoSQL data stores. This project will form the basis of a case study to demonstrate that this system can easily be deployed in practice without effecting user experience or system performance.