December 2020

March 10th, 2021


  • Chandra Thapa, Seyit Camtepe: Paper entitled “Precision Health Data: Requirements, Challenges and Existing Techniques for Data Security and Privacy,” accepted and published by the Elsevier journal “Computers in Biology and Medicine” (impact factor = 3.434) available online at

Highlights: This paper is a baseline paper for new researchers interested in embarking on the health care data analytics domain. The detailed backgrounds, including the proposed conceptual system model for security and privacy, presented in this paper, enable new researchers to overview the current state-of-art in privacy/security and machine learning for health data. Recently, an American company named “Fortanix,” which is working on confidential computing, has shown interest in working with our group, citing this paper.

Abstract:  Outsourcing machine learning inference services to the cloud is getting increasingly popular. However, this also entails privacy risks to the provider’s proprietary model and the client’s sensitive data. Focusing on inference with decision trees, this paper proposes a framework for securely and efficiently outsourcing decision tree inference. The paper has appeared in the top security journal with IF 6.864.

Abstract: Sharing the medical data faces critical privacy obstacles with the increasingly strict legal regulations on data privacy. In this paper, we present the design of a novel system enabling privacy-preserving DTW-based analytics on distributed medical time-series datasets. The paper has appeared in the top security journal with IF 6.864.


  • A contract signed with Bit-Cores to investigate how our patented EnerID blockchain can be used to strengthen the functionality of distributed file systems developed by Bit-Cores. The project will start on 7 Dec, 2020.  
  • Highlight on one of our projects: Automatic Generation of Security-Centric Description for Cyber Threats, the PhD project of Tingmin (Tina) Wu, under the supervision of Dr Cecile Paris and Dr Surya Nepal from CSIRO’s Data61, and Professor Yang Xiang and Dr Sheng Wen from Swinburne University of Technology.

The project proposes to generate security-centric descriptions to help the users comprehend the cybersecurity information so that they can apply the advice it contains in practice. We implemented a system that learns users’ security concerns and linguistic preferences to generate personalised security-centric descriptions. We then built a large collection of user-accessible security texts and conducted a subjective study to measure the level of users’ understanding of security texts. We also analysed the trending topics across different sources over time to create knowledge patterns for users and help predict cyber-attacks. Furthermore, to improve users’ ability to understand security texts, we developed a framework to build a user-oriented security-centric dictionary from multiple sources. A language model was developed to extend the dictionary automatically. To evaluate the effectiveness of the dictionary, we developed a tool as a service to detect technical terms and explain their meanings to the user in pop-ups. The results of a subjective study to measure the tool’s performance showed that it could increase users’ ability to understand security articles significantly.


  • Let’s meet one of our recent graduates M.A.P. Chamikara Mahawaga Arachchige

I’m M.A.P. Chamikara, a research fellow at Data61, CSIRO, and a 4th year Ph.D. student at RMIT University, Melbourne, Australia (Thesis Title: “Scalable Data Perturbation for Privacy-Preserving Large Scale Data Analytics and Machine Learning”).   My current work focuses on enforcing privacy, security, and trustworthiness on large scale machine learning and big data and data stream sharing for analytics. I investigate areas such as differential privacy, deep learning, distributed machine learning (FedML, SplitNN), Blockchain, and smart contracts. During my Ph.D., we developed over seven novel approaches published in highly reputed journals such as IEEE transactions on industrial informatics, IEEE Internet of Things Journal, and Elsevier Information Sciences. During my Ph.D., I enjoyed working under the supervision of Dr. Dongxi Liu (Data61), Dr. Seyit Camtepe (Data61), A/Prof. Ibrahim Khalil (RMIT), and A/Prof. Peter Bertok (RMIT). I must also mention the valuable support rendered by Dr.  Marthie Grobler (Data61) during my research work at Data61. In addition to the Ph.D. research work, RMIT and Data61 allowed me to engage with many talented researchers.  Consequently, I was able to collaborate and publish papers with many Data61 scientists and RMIT scientists. I am thankful to Data61, an RMIT, for all these valuable experiences.

New starters:

  • M.A.P. Chamikara Mahawaga Arachchige and Zhi Zhang joined as research fellows. Welcome both!
  • 22 students started as vacation students this November, 16 of them working on Cyber Security CRC projects and problems.


2 articles about how our TrustStore technology is being used.

As it launches its highly secure VeroCard multi-factor authentication device after years of development, Australian cybersecurity firm VeroGuard Systems is on track to create hundreds of new security and engineering jobs in Adelaide and Melbourne by 2023.

The firm – which emerged from Adelaide’s Defence-heavy innovation sector and now enjoys a strategic partnership with CSIRO and a global partnership with Microsoft – has spent 17 years refining the technology behind its newly launched VeroCard.

Melbourne-headquartered hi-tech firm VeroGuard Systems has released a locally developed digital identity platform which, after several years of testing, is now available for purchase. The platform also has its own secure cloud storage known as VeroVault, developed in collaboration with CSIRO. It uses technology known as TrustStore that has been developed by Data61. “It is now more important than ever for organisations to be thinking about whether they have the right cyber security systems and practices in place to future-proof their businesses,” said Data61 director Jon Whittle.


  • Cutting Edge Science and Engineering Symposium: Advances in personalised healthcare and wellbeing support technologies was successfully completed as a virtual symposium: 19 – 20 November 2020.
  • Congratulations to all the winners of November SCS awards, including:
    •  Muhammed Esgin, Science Excellence
    • Smart Shield team, Customer First
    • Muhammad Ejaz Ahmed, Collaboration


  • Special Session on Humans And Cyber Security (HACS2020)

The special session on Humans and Cyber Security (HACS-2020) will be taking place in a virtual format on the 2nd of December 2020 (EDT), again co-hosted with IEEE CIC (Collaboration and Internet Computing), IEEE CogMI (Cognitive Machine Intelligence) and IEEE TPS (Trust, Privacy and Security of Intelligence Systems, and Applications).

Keynote Speaker: Professor Debi Ashenden

Debi holds the DST Group-University of Adelaide Chair in Cybersecurity. In addition, she is Professor of Cyber Security at the University of Portsmouth (UK) and a visiting Professor at Royal Holloway, University of London (UK).  Debi’s research interests are in the social and behavioural aspects of cyber security – particularly in finding ways of ‘patching with people’ as well as technology. She is currently researching the socio-technical issues around cloud computing and DevSecOps, as well as exploring the implications of algorithmic decision-making.

Debi was previously Head of the Centre for Cyber Security at Cranfield University at the Defence Academy of the UK and was a member of the UK MOD’s Defence Science Expert Committee.  She has worked extensively across the public and private sector for organisations such as UK MOD, GCHQ, Cabinet Office, Home Office, Euroclear, Prudential, Barclaycard, Reuters and Close Bros. She has had a number of articles on cyber security published, presented at a range of conferences and co-authored a book for Butterworth Heinemann, Risk Management for Computer Security: Protecting Your Network & Information Assets.

For more information: