December 2021- January 2022

March 10th, 2022

Publications

 

 

  • Indika Kumara, Mohamed Hameez Ariz, Mohan Baruwal Chhetri, Majid Mohammadi, Willem-Jan Van Den Heuvel, Damian, A. Tamburri, FOCloud: Feature Model Guided Performance Prediction and Explanation for Deployment Configurable Cloud Applications. Accepted to IEEE Transactions on Services Computing (CORE A*). The paper proposes a performance engineering approach for deployment configurable cloud applications that (i) uses feature modelling to structure and constraint the valid deployment space by modelling the commonalities and variations in the different deployment options and their interdependencies, (ii) uses sampling and machine learning to incrementally and cost-effectively build a performance prediction model whose input variables are the deployment options and the output variable is the performance of the resulting deployment variant, and (iii) uses Explainable AI techniques to provide explanations for the prediction outcomes of valid deployment variants in terms of the deployment options.
  • X Zhu, S. Wen, S. Camtepe, Y. Xiang, “Fuzzing: A Survey for Roadmap”, (To Appear) ACM Computing Surveys (CSUR, CORE A*), 2022. This is the final publication of the Data61 scholarship student X. Zhu. Xiaogang has a great expertise on fuzzing. He used his expertise systematically review and analyze the gaps as well as their solutions, considering both breadth and depth. This survey can be a roadmap for both beginners and advanced developers to better understand fuzzing.
  • J. R. Dawson, George Hobbs, Yansong Gao, Seyit Camtepe, Josef Pieprzyk, Yi Feng, Luke Tranfa, Sarah Bradbury, Weiwei Zhu, Di Li, “Physical Publicly Verifiable Randomness from Pulsars”, (To Appear) Astronomy and Computing,   2022. This is the final publication of the Data61 / S&A Space FSP projects. The work has produced an MSc thesis, vacation student projects, a patent and this publication with potential follow-up collaboration on “Application of Pulsar”. Work involved observation from two very famous receivers in Australia (Parkes) and China (FAST). Up-to-our knowledge, the proposed solution is the first publicly (universally) observable/verifiable, unpredictable and non-malleable natural source of randomness at millisecond frequencies, which does not require any trusted server or authority to work. Hence, it can be considered as a reference for any commercial, political or military conflicts (e.g., post-soviet treaties). The same source also includes signal components for precise timing and navigation beyond Earth’s orbit or on the Earth. The team is currently looking for funding opportunities to build the world’s first truck mountable/deployable pulsar receiver for various Earth to space applications, including randomness, cryptography (data confidentiality), synchronization/key agreement, timing, and navigation.
  • Gao, M. Kim, C. Thapa, S. Abuadbba, Z. Zhang, S. Camtepe, H.  Kim, S. Nepal, “Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things”, (to Appear) IEEE Transactions on Computers, (ToC, CORE A*), 2022. While many published talk about how distributed ML can be used in edge and IoT systems, the published work is one of the first attempts to experimentally evaluate and optimise distributed ML on IoT devices.
  • Cong Zuo, Shi-Feng Sun, Joseph K. Liu, Jun Shao, Josef Pieprzyk, and Lei Xu. Forward and Backward Private DSSE for Range Queries, IEEE Transactions on Dependable and Secure Computing, Publication Date: JANUARY/FEBRUARY 2022, Volume: 19, Issue: 1, pp. 328–338

Projects

  • Contract signed for “Defence Innovation Hub – Artificial Intelligence Applications in Defence” to develop a portable technology demonstrator to identify the direction of angle and waveform of unknown radio signals by utilising artificial intelligence acceleration application specific integrated circuit.  Fully funded, $900k over 1 year.  Hajime Suzuki to lead the project in collaboration with Information Security and Privacy Group, Cyber Physical Systems Research Program and Space and Astronomy Business Unit.
  • The project “Partially Order Preserving Tokenization” started in December 2021 and will end in June 2022. This project is supported by the company Comforte and Innovation Connections offered by the Department of Industry, Science, Energy and Resources.  Comforte has the a data-security product for tokenization and it would like to incorporates our order-preserving indexing techniques into their tokenization product.  Dongxi Liu will lead the project 
  • The ‘Cyber Security Framework for the Chilean mining industry’ contract with CSIRO Chile has been signed and the project commenced. CSIRO Chile and Alta Ley Corporation are partnering for the creation of a Cyber Security Centre for the Chilean mining industry. As part of this activity CSIRO Chile has entered into an agreement with Alta Ley Corporation to produce a Cybersecurity Baseline and Action Plan for the industry. CSIRO Australia, through Data61, will produce a Cybersecurity Framework, a key component of the project that the baseline and action plan will rely on. Marthie Grobler and Mohan Baruwal Chhetri will work on this project.
  • EPSRC  Grant: UK-Australia centre in a secure internet of energy: supporting electric vehicle infrastructure at the ‘edge’ of the grid https://www.ukri.org/news/international-collaborations-to-develop-technologies-of-tomorrow/ EPSRC  Grant: UK-Australia centre in a secure internet of energy: supporting electric vehicle infrastructure at the ‘edge’ of the grid, UK-Australia centre in a secure internet of energy: supporting electric vehicle infrastructure at the ‘edge’ of the grid, Led by: Professor Rajiv Ranjan, Newcastle University Partners include Cardiff University, University of Sydney (Australia), and Commonwealth Scientific and Industrial Research Organisation (CSIRO) (Australia). Surya Nepal is the lead from CSIRO. the EPSRC funding: £1.5 million https://www.ukri.org/news/international-collaborations-to-develop-technologies-of-tomorrow/
  • ARC DP Grant: MemberGuard: Protecting Machine Learning Privacy from Membership Inference   https://rms.arc.gov.au/RMS/Report/Download/Report/a3f6be6e-33f7-4fb5-98a6-7526aaa184cf/230 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. Swinburne University of Technology; $450,000.00; Dr Sheng Wen; Dr Surya Nepal
  • The IAM project successfully delivered a new tool to support human-in-the-loop analysis and remediation of planned organisational changes on users’ access entitlements. Field testing of the work is underway for production use.
  • The Kick-start project with Global Bionic Optics has completed on 19 Jan 2022.  In this project, we have analysed the QuantumCrypt scheme, developed by Global Bionic Optics, for secure face recognition and evaluated its performance. A report has been delivered to and accepted by the customer. The project status in O2D is also updated for the final invoice.

Join us

  • Postdoctoral Fellow opportunities

https://jobs.csiro.au/job/Sydney%2C-NSW-CSIRO-Postdoctoral-Fellowship-in-Collaborative-Intelligence-Cybersecurity/802708400/?locale=en_GB

https://jobs.csiro.au/job/Various-Data61-PhD-Scholarships/796808000/?locale=en_GB

Staff

Welcome to Olivier de Vel

Dr Olivier de Vel obtained MSc(I Hons) from Waikato University (New Zealand) and a PhD in Electronic Engineering from the Institut National Polytechnique of Grenoble (INPG, France). He was previously Principal Scientist (Cyber) in the Cyber and Electronic Warfare Division, Defence Science and Technology (DST) Group, Department of Defence, Australia.

Dr de Vel has worked at several national and international universities, in government research agencies (e.g., CNRS, ORSTOM, DSIR), and in industry R&D laboratories (BHP Billiton mining, GECO oil & gas industry). Dr de Vel joined DST Group in 1999 to set up and provide the scientific R&D leadership in cyber forensics. In 2005, he was appointed Research Leader in Cyber Assurance and Operations to lead the DST Group broad spectrum cyber-security program in the C3I Division. He was appointed Principal Scientist (Cyber) in 2015. Dr de Vel has developed collaborative research programs with government research entities as well as universities. His expertise is in the area of artificial intelligence and machine learning for cyber-security and he has published over 100 papers in computer science, digital forensics and machine learning.

We are saying goodbye to Hamza Sellak, Sushmita Ruj and Raj Gaire who have recently left our group.

Sushmita is joining UNSW as a Senior Lecturer at the School of Computer Science and Engineering, UNSW, Sydney and Raj is joining KPMG as KPMG as an Associate Director for Defence and National Security.

We hope all the best for them in their new journey and thank them for what they provided to the whole group.

 

Students

  • Summer vacation scholars

Hi, my name is Caitlin and I’m about to enter my fifth and final year of Bioinformatics Engineering and Ecology at UNSW.I am very passionate about the environment, and you will often find me outdoors either at the beach or going for bushwalks in my spare time.In the future I would love to combine my love for nature and my technical computing skills to help solve the environmental problems we face.Over this summer I will be working with Marthie Grobler, Kristen Moore, and Tina Wu to look at human factors affecting phishing attacks and user susceptibility to them and then use human-centred AIto help defend against such attacks.

Hi, my name is Kurtis and I’m currently at the tail end of my bachelor’s in electrical engineering degree from UNSW. I’ve always loved computers and seeing the industry evolve has been a great source of inspiration. I’m truly excited to see the limitations of computation and all the possible applications that would have been blasphemy years ago. Under the tutelage of Dr. Hajime Suzuki, we will be exploring the capabilities of software defined radio and examining their use in real-time spectrum analysis. The world of FPGAs is quite daunting – but if all goes right we should be able to parallelize computationally intensive processes and have a portable, practical spectrum analysis tool.

  • let’s meet one of our students:

My name is Viet Vo. I am a Ph.D. student in The Department of Software Systems and Cybersecurity (SSC) at Monash University. I am expecting to submit my thesis in mid-December 2021. The work is titled “Efficient mitigation of leakage-abuse attacks in searchable encryption”. The research aimed to improve the security of searchable encryption against practical threat models in dynamic database settings. I am grateful to have had opportunities to collaborate with many enthusiastic staff and students of CSIRO Data61. I would also like to express my gratitude to Dr. Surya Nepal, who closely follows my Ph.D. journey. During the Ph.D. course supported by CSIRO Data61, our joint works have been published in ACM CCS’18, ACNS’19, ACNS’20, and IEEE TKDE’21, and one paper is to be submitted to ACM CCS’22. Although my Ph.D. journey with CSIRO Data61 is about to end soon, I will keep collaborating with researchers from CSIRO in the field of security and privacy.

 

Events

  • Data61 and DSTG Cyber Security Summer School new date 21-23/2/22

Due to the recent announcements and future dates set for the relaxing on domestic and international border restrictions, the organising committee has made the decision to move our forthcoming event to 21 to 23 February 2022. This event will still be held in a hybrid online/in-person mode, but with the added benefit of an increased proportion of in-person participation, enabled by the new travel rules.  We hope that you are as excited as us at the possibility to meet in person, even if it means a change in date.

The CSIRO’s Data61 & DSTG Cyber Security Summer School (CSSS) (https://research.csiro.au/csss/), in collaboration with the University of Queensland, is an annual summer school focusing on a range of cyber security topics, bringing the Australian cyber ecosystem together. The CDNG Technology and Science Conference (https://wp.csiro.au/cdng/), in collaboration with Macquarie University, is a first of its kind scientific and technology focused Cyber Defence Conference, with the aim to have the community of Cyber-Security under the “Next Generation Defence Technologies | Cyber Research” program in collaboration with DST-Data61 and partner universities meet together, expose relevant research activities and discuss future collaborations. This year, the two events will jointly be hosted at Customs House Brisbane, 21 to 23 February 2022.Attendance is free, subject to invitation.

https://research.csiro.au/csss/ Bringing together the Australian cyber security ecosystem

Regular events

  • SAO seminars in collaboration with the Cyber Security CRC

https://research.csiro.au/cybersecurity-quantum-systems/our-sao-seminars/

Talks/conferences

  • Marthie Grobler presented the keynote address at the International Conference on Applications and Techniques in Information Security (ATIS) 2021, ATIS 2021 (conferences.academy).
  • Josef Pieprzyk gave the Jennifer Seberry Lecture at the ACISP 2021 Conference. The title of the lecture was Asymmetric Numeral System and Cryptography (https://data61dsslab.github.io/acisp2021/)
  • Dr Kristen Moore | UNSW IFCyber

ML Enabled Cyber Deception with Dr Kristen Moore 9 – 10 am 9 March 2022

Cyber Deception is increasingly valuable as a tool for breach detection, theft discovery and threat intelligence.  The key to successful deception is realistic mimicry of the digital world. This talk gives a brief overview of some cyber deception projects our team has been working on within our Cyber Security CRC project, using ML to enable automated and scalable generation of realistic content and behaviour. We then dive into the details of one particular project, which focuses on simulating social network communications. To read more about this topic and to view Dr Moore’s bio please click here  To join the seminar please click here.