Day 1 - Data Science, Machine Learning, and AI in Cyber Security
Keynote
Securing Graph Neural Networks in MLaaS
Abstract:
Graph Neural Networks (GNNs) extend the benefits of deep learning to graph data. In practice, their applications span from common utilities such as recommendation systems and fraud detection, to advanced domains such as drug discovery and physics simulation. Due to the increasing popularity of GNNs, commercial Machine Learning as a Service (MLaaS) platforms have integrated graph learning development tools for launching GNN services on the cloud, e.g., Amazon SageMaker integrated DGL. Despite the convenience and low cost of model development and deployment, such service is facing critical security challenges. In this talk, I will first overview the architecture of GNNs in MLaaS and elaborate on practical threats against privacy and integrity of GNNs. Then I will present our recent effort in detecting and counteracting training data misuse in GNNs. Along the line, I will also pinpoint open problems and future directions in this area.
Short Biography:
Xingliang Yuan is currently an Associate Professor in the School of Computing and Information Systems, the University of Melbourne. Before that, he was a faculty member at Monash University from 2017-2024. He has a keen interest in designing systems and protocols to address real-world privacy and security challenges. His research has been supported by the Australian Research Council, CSIRO, Australian Department of Home Affairs, Australian Department of Health and Aged Care, and the Oceania Cyber Security Centre. His work has been published in major venues of computer security and systems, such as CCS, S&P, USENIX Security, NDSS, TDSC, TIFS, etc. He is a recipient of the Dean's Award for Excellence in Research by an Early Career Researcher (2020), and the Faculty Teaching Excellence Award (2021). He is a co-recipient of the best paper award in the European Symposium on Research in Computer Security 2021. He is on the editorial board of IEEE Transactions on Dependable and Secure Computing and IEEE Transactions on Service Computing. He is a track co-chair of ICDCS'24, PST'24, and program co-chair of SecTL'23 and NSS'22. He is an ARC future fellow and a senior member of IEEE.
Industry Panellists / Speakers
Mayur is an Innovative leader in Threat Exposure Management Solutions, adept at guiding organisations through the complexities of cyber risk. As Associate Director at EY, he spearheads innovative strategies to identify, assess, and mitigate threats, ensuring clients stay resilient in the face of evolving cyber threats. With a focus on proactive threat intelligence and cutting-edge technologies, Mayur empowers teams to safeguard digital environments effectively and is dedicated to driving tangible results and fostering a culture of security excellence.
Dr Sebastien Wong leads a team of scientists and engineers conducting applied research into computer vision within Information Sciences Division in Defence Science Technology Group. Sebastien holds a Bachelor of Computer Systems Engineering (with honours) from Curtin University, a Master of Electronic Systems Engineering and a Ph.D. in Computer Science, both from the University of South Australia. Sebastien also holds a Graduate Diploma in Scientific Leadership from the University of Melbourne and is a graduate of the Australian Institute of Company Directors. Sebastien has over two decades of experience in translating research algorithms into operational solutions for Defence, Mining and Agriculture. Sebastien conceived and led the creation of a multi-award winning AgTech product for mapping and monitoring the worlds high-value crops, which was used to map Australia’s vineyards. Sebastien's current team is working on problems that range from finding dark fishing vessels using synthetic aperture radar (SAR) imagery, to enhancing situational awareness for drone video operators. Sebastien is passionate about applying his experience in computer vision and machine learning to transform Defence by providing intelligent tools to decision-makers.
Dr Xiaoning (Maggie) Liu is a Lecturer (aka Assistant Professor) at the School of Computing Technologies, RMIT University, Australia. Her research pivots on data privacy and security related to machine learning, cloud computing, and digital health. Her current focus is on designing practical secure multiparty computation protocols and systems to its applications in privacy-preserving machine learning. She earned her Ph.D. in Computer Science degree in 2022 from RMIT University. In the past few years, her work has appeared in prestigious venues in computer security, such as IEEE Transactions on Dependable and Secure Computing (TDSC), IEEE Transactions on Information Forensics and Security (TIFS), USENIX Security Symposium, and European Symposium on Research in Computer Security (ESORICS). Her research has been supported by Australian Research Council, and CSIRO. She is the recipient of the Best Paper Award of ESORICS 2021.
Guru is technical specialist in Data and AI at Microsoft. He has background in Engineering and has worked with Microsoft IT and Research and has patents in the area of touchless input algorithms. He engages with customers, understanding their requirements, and helping them architect and achieve business benefits on the Azure cloud.