Halil Ali is a Lecturer in Data Science (Education Focused) at the School of Computing Technologies, RMIT University. His research spans privacy-preserving machine learning, blockchain technologies, and cybersecurity. Key research areas include federated learning , quantum-enhanced AI , secure biometrics , edge unlearning , and privacy in healthcare data . His recent publications focus on resilient AI systems , blockchain applications , and ethical data handling in emerging technologies. His work demonstrates expertise in integrating machine learning with blockchain security across domains like IoT, smart grids, and metaverse healthcare. He contributes to practical frameworks for zero-trust architectures , lightweight consensus protocols , and quantum-classical hybrid models .
Dr. Kanchana Thilakarathna is a Senior Lecturer in Distributed Computing at the University of Sydney's School of Computer Science, and a member of the Centre for Distributed and High Performance Computing. They hold a PhD from the University of New South Wales (UNSW) and a B.Sc. Eng (Hons) from the University of Moratuwa, Sri Lanka. Prior to academia, they worked as a Research Scientist at CSIRO/Data61 and had industry experience as a Mobile Radio Network Engineer. Research Interests : Dr. Thilakarathna focuses on cybersecurity, privacy in mobile and IoT systems, mixed reality privacy, and distributed computing platforms. Their work emphasizes user-centric solutions like the Yalut social media app, which enables decentralized data sharing. Key themes include privacy-preserving techniques, edge computing, and secure federated learning frameworks. Recent Work : Recent articles (2023–2025) explore machine unlearning for large language models, federated learning security, and IoT network slicing using P4 programmability. Their work on synthetic video traffic generation (VideoTrain++) and drone detection (DronePrint) demonstrates cross-disciplinary innovation. Awards : Malcolm Chaikin Prize (2015), Meta Research Awards (2020/2022), and Heidelberg Laureate Fellowship (2019). Grants : ARC Research Hub for Future Digital Manufacturing (2024), NSW Defence Innovation Network Projects (2024/2021), and Facebook Research Awards (2022/2020). Students : Advising 4 current PhD students on topics like wireless trust establishment and machine unlearning. Labs/Teams : Part of the Centre for Distributed and High Performance Computing and Sydney Nano Institute.
Mehrtash Tafazzoli Harandi is an Associate Professor in the Department of Electrical and Computer Systems Engineering at Monash University, part of the Faculty of Engineering. His research focuses on machine learning and computer vision, particularly visual data analysis, with contributions to geometric deep learning, continual learning, and medical imaging. He holds editorial roles at IET Computer Vision , Frontiers in Imaging , and Journal of Imaging . Education & Previous Affiliations: Prior to Monash, he worked at NICTA (Canberra & Queensland Research Labs) and CSIRO-Data61. His Erdős number is 4 via a collaboration path through Richard Hartley. Research Interests: His work spans geometric learning, diffusion models, medical image analysis, and sustainable AI applications. Key areas include unlearning mechanisms in AI, 3D reconstruction compression, and robust MRI reconstruction using contrastive learning. Grants & Projects: He leads projects funded by ARC, US Air Force, and industry collaborations, including 'Can Machines Unlearn?' (ARC, A$790k) and 'Exploiting Geometries of Learning' (ARC, A$420k). His work addresses challenges in lifelong learning, model adaptation, and trustworthy AI from limited data. Awards: Recipient of Best Recognition Paper (IEEE DICTA 2013), NICTA Impact Award (2015), and multiple outstanding reviewer recognitions at top conferences. Teaching: Teaches courses on neural networks, computer vision, and advanced data analysis at Monash University. Supervises PhD students with a focus on mathematical and computational proficiency. Labs/Teams: Collaborates with the Australian Center for Robotic Vision (ACRV) and contributes to interdisciplinary projects at CSIRO-Data61. His research group explores cutting-edge AI applications in healthcare, manufacturing, and environmental sustainability.
Professor Dinh Phung is the Head of the Department of Data Science & AI at Monash University. His research focuses on machine learning, deep learning, generative AI, and robust AI systems. He has authored over 250 publications, with applications in NLP, computer vision, digital health, and cybersecurity. Phung holds a PhD and BSc(Hons) in Computer Science from Curtin University. He leads major projects like 'Can Machines Unlearn?' and 'Trustworthy Generative AI', funded by the Australian Research Council and the Department of Defence. Education: Doctor of Philosophy, Computer Science, Curtin University (2005) Bachelor of Science (Honours), Computer Science, Curtin University (2001) Research Interests: Machine learning, deep learning, and generative models Optimal transport and Bayesian methods Robust and trustworthy AI Applications in digital health, cybersecurity, and autism research Key Projects (2023–2029): Can Machines Unlearn? (2025–2029): Safety in AI Trustworthy Generative AI (2024–2026): Foundation models Robust Machine Learning via Optimal Transport (2023–2025) Awards and Grants: Australian Research Council grants for AI safety and robustness Department of Defence funding for robust learning systems Collaborations: Global partnerships in AI ethics, cybersecurity, and healthcare. Active advisory roles, including with the Victorian Parliamentary Library.
Dr. Hongsheng Hu is currently a Lecturer in the School of Information and Physical Sciences at the University of Newcastle, Australia, specializing in the Data Science and Statistics focus area. Prior to this position, he served as a Postdoc Research Fellow at CSIRO's Data61 from October 2022 to August 2024. His academic journey includes a Doctor of Philosophy in Computer Systems Engineering from the University of Auckland in New Zealand, establishing his foundation in advanced computing systems. Dr. Hu's research centers on enhancing the trustworthiness of machine learning systems, with particular emphasis on identifying critical privacy vulnerabilities within machine learning models and developing robust defensive strategies. His work spans several key domains including adversarial machine learning (30% focus), statistical data science (30% focus), and data and information privacy (40% focus). He investigates membership inference attacks, machine unlearning techniques, and privacy-preserving mechanisms in federated learning environments. His research addresses fundamental challenges in AI security, exploring how machine learning models can be compromised through sophisticated privacy attacks and developing methods to mitigate these vulnerabilities while maintaining model utility. Analysis of Dr. Hu's publication record reveals a strong research trajectory focused on machine learning security and privacy. His work consistently addresses vulnerabilities in machine learning systems, particularly examining membership inference attacks, machine unlearning mechanisms, and privacy-preserving techniques in federated learning. The research spans top-tier venues including IEEE Security & Privacy, USENIX Security, NDSS, NeurIPS, IJCAI, AAAI, and WWW, demonstrating both technical depth and recognition by the research community. His publications show an evolving focus from foundational privacy attacks to developing more sophisticated unlearning techniques and robust defense mechanisms, with increasing citation counts indicating growing impact in the field. Active Program Committee member for USENIX Security, NDSS, ICLR, IJCAI, WWW, ICDM, ECML, and PKDD Invited reviewer for IEEE Transactions on Information Forensics and Security (TIFS), IEEE Transactions on Dependable and Secure Computing (TDSC), IEEE Transactions on Pattern Analysis and Machine Intelligence (IPAMI), and ACM Computing Surveys (CSUR) Dr. Hu currently serves as Course Coordinator for STAT6020 and STAT2020 Predictive Analytics at the University of Newcastle. As an academic supervisor, he co-supervises one PhD student working on 'Identifying and Mitigating Vulnerability in Recommender Systems' at Macquarie University. His research collaborations span multiple countries, with significant publication counts in Australia (18), China (12), New Zealand (10), and the United States (7), reflecting an active international research network focused on AI security challenges.
Dr Miao Xu is a Research Fellow at the University of Queensland (UQ), affiliated with the School of Electrical Engineering and Computer Science within the Faculty of Engineering, Architecture and Information Technology. She holds an Australian Research Council DECRA Fellowship (ARC DECRA), recognizing her early-career research excellence. Her research focuses on machine learning, data science, and time series analysis, with applications in healthcare, materials science, and algorithmic fairness. Dr Xu's work addresses challenges in noisy label handling, unlearning mechanisms, and adaptive modeling for irregular data. Education: She earned a Doctor of Philosophy (PhD) from Nanjing University. She is actively involved in supervising research and contributes to the Centre for Enterprise AI at UQ. Research Interests: Dr Xu’s expertise spans machine learning , time series analysis , deep learning , and unsupervised learning . Her recent work emphasizes robust learning with noisy or incomplete labels, model unlearning, and applications in alloy design and medical informatics. She explores methods like instance-attention GNNs for irregular time series and confidence-guided techniques for adversarial attack detection. Publications: Her recent work includes advancements in GNN-based time series modeling, bias mitigation in text classification, and active learning for alloy design. Key themes include improving generalization, reducing algorithmic bias, and enhancing model transparency. Awards: Her ARC DECRA fellowship (202X–202X) supports her research on data-driven methodologies. Supervision & Grants: Available for PhD supervision in machine learning and data science. Her grants include funding for projects in unlearning mechanisms and spatiotemporal modeling. Labs/Teams: Affiliated with the Centre for Enterprise AI at UQ, collaborating on enterprise-scale AI applications and interdisciplinary research.
Dr. Xiaoyu Xia is a Lecturer (equivalent to Assistant Professor in North America) in Cybersecurity & Software Systems at RMIT University's School of Computing Technologies. He received his PhD with the prestigious Alfred Deakin Medal from Deakin University, Australia, and has established himself as a leading researcher in distributed systems and cybersecurity with over 50 peer-reviewed publications in top-tier venues including IEEE S&P, ACM WWW, and IEEE Transactions. Dr. Xia's research spans critical areas at the intersection of computing and security: System Privacy and Security Distributed Systems and Edge Computing AI Privacy and Machine Learning Systems Sustainable Computing Cybersecurity and Privacy-Preserving Technologies His recent work demonstrates a clear trajectory toward developing practical privacy-preserving frameworks for emerging technologies, particularly in edge computing environments and large language models. Dr. Xia has made significant contributions to machine unlearning, secure data management in distributed systems, and energy-efficient edge computing solutions that balance performance with sustainability concerns. Dr. Xia has received notable recognition for his scholarly impact: World's Top 2% Scientists by Stanford University (2022-2024) Alfred Deakin Medal for PhD research excellence (2021) Teaching Excellence Award from Swinburne University of Technology (2021) As an active researcher, Dr. Xia currently leads multiple funded projects including an ARC Discovery Project grant worth over $500,000 for developing privacy-aware intelligent digital twins for secure critical infrastructures. He is open to supervising motivated PhD students with interests in system security and privacy, and distributed ML systems. Dr. Xia serves the academic community through editorial roles as Associate Editor for IEEE Transactions on Dependable and Secure Computing and as a Review Board Member for IEEE Transactions on Parallel and Distributed Systems, and regularly participates in program committees for major conferences including ACM WWW and IEEE ICDCS.
Professor Xun Yi is a faculty member at RMIT University's School of Computing Technologies, specializing in cybersecurity, data privacy, and distributed computing. His research focuses on privacy-preserving technologies in cloud systems, blockchain applications, federated learning, and secure communication protocols. He has published over 150 papers in top-tier journals and conferences, including IEEE Transactions on Dependable and Secure Computing. Since 2014, he has served as an Associate Editor for the IEEE Transactions on Dependable and Secure Computing, and has organized major events like the Australasian Information Security Conference (AISC) in 2015 and 2016. Professor Yi actively supervises PhD and Master's research projects, focusing on topics like secure IoT systems, privacy-aware machine learning, and blockchain-enabled frameworks. His work emphasizes practical solutions for real-world challenges in data security and privacy. Research Interests: Data Privacy, Cyber Security, Cloud Security, Wireless/Mobile Security, Applied Cryptography Blockchain-based Systems, Federated Learning, Privacy-Preserving AI Recent Contributions: Developed frameworks for secure data aggregation in smart grids and healthcare systems Advanced techniques for privacy-preserving federated learning and graph neural networks Contributed to standards for secure authentication in vehicular networks (VANETs) Supervision: Open to mentoring students in cybersecurity, privacy-enhancing technologies, and IoT security.
Shui Yu is a Professor of the School of Computer Science in the Faculty of Engineering and Information Technology at the University of Technology Sydney (UTS), where he also serves as the Deputy Chair of the UTS Research Committee. His academic career spans over 20 years in Australia and 7 years in China, with additional teaching experience in Hong Kong and Indonesia. He has developed more than 10 units in cybersecurity, computer science, data analytics, and computer games, serving as the Course Director for Computer Science undergraduate programs. Professor Yu's research interests center on cybersecurity, privacy, networking aspects of Big Data, and applied mathematics for computer science. He pioneered the field of 'networking for big data' in 2013 and edited the seminal book 'Networking for Big Data' published in 2015. His work has practical applications in industry, including Amazon Cloud's auto-scale strategy against distributed denial-of-service attacks. Current research focuses include privacy and security concerns associated with big data, security issues in smart grids, anonymous transactions on Blockchain, and anonymous communication for web browsing privacy. Analysis of his recent publications reveals a strong research trajectory spanning cybersecurity, privacy-preserving technologies, networking for big data, and applied mathematics. His work shows increasing focus on quantum-resistant cryptography, federated learning security, and adversarial robustness in AI systems. The interdisciplinary nature of his research bridges theoretical foundations with practical applications in IoT, blockchain, and cloud environments. Fellow of IEEE (2023) Distinguished Lecturer of IEEE Communications Society (2018-2021) Distinguished Visitor of IEEE Computer Society (2022-2024) Professor Yu has secured numerous research grants from the Australian Research Council, including current projects on privacy and fairness in high intelligence models (DP240100955), improved security and privacy for online platforms (LP220200808), and secure blockchain for financial applications (LP220100453). He has served on editorial boards of multiple IEEE journals including IEEE Communications Surveys and Tutorials, IEEE Communications Magazine, and IEEE Internet of Things Journal. His service extends to organizing major conferences such as IEEE Globecom 2015 and IEEE INFOCOM 2016-2017.
Dr Alina Bialkowski is a Senior Lecturer at the School of Electrical Engineering and Computer Science , part of the Faculty of Engineering, Architecture and Information Technology at The University of Queensland. Her research focuses on interpretable machine learning and computer vision to enhance AI transparency and solve real-world challenges. Prior to joining UQ in late 2017, she held postdoctoral positions at University College London (2015–2017), where she studied human perception in driving, and Disney Research Pittsburgh (2014), analyzing team sports using spatiotemporal data. Dr Bialkowski earned her PhD and Bachelor of Engineering (Electrical Engineering) from Queensland University of Technology, Australia. Her doctoral research centered on group behavior analysis from visual and spatiotemporal data, with applications in sports analytics and intelligent surveillance systems. Her research interests span medical imaging (especially electromagnetic imaging of strokes), human attention modeling in driving, intelligent transport systems , surveillance systems , and sports analytics . She emphasizes explainable AI to bridge the gap between technical systems and human understanding, employing methods like feature visualization and attribution. Her work also explores sensors for non-invasive imaging and machine learning frameworks to ensure ethical AI. Dr Bialkowski has received significant recognition, including the Best Paper Prize at the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) . Her research has led to 6 international patents with collaborators such as Disney Research, Toyota Motor Europe, and The University of Queensland, focusing on electromagnetic imaging and AI-driven solutions. She actively contributes to interdisciplinary projects like The Lanyard Project (traffic sensor fusion) and co-authored a SmartSat CRC-funded research report on machine learning for satellites. Dr Bialkowski is available for supervision and advocates for AI systems that integrate human-centric principles into their design and evaluation.
Trung Le is a Lecturer in the Department of Data Science & AI at Monash University. His research focuses on deep generative models, kernel methods, optimization in machine learning, and Bayesian inference, with applications to supervised learning, adversarial learning, and cyber security. He holds a PhD in Computer Science from the University of Canberra (2013). Key projects include the Australian Research Council-funded initiatives such as 'Can Machines Unlearn? Toward Next-Generation Safe Artificial Intelligence' (2025–2029) and 'Trustworthy Generative AI: Towards Safe and Aligned Foundation Models' (2024–2026). His work contributes to UN SDG 4 (Quality Education) through advancements in AI ethics and safety. Education: PhD in Computer Science, University of Canberra (2013) Research Areas: Continual Learning, Diffusion Models, Domain Adaptation, Adversarial Machine Learning Awards: KDD 2023 Best Student Paper Award, Imagine Cup 2010 Australia First Prize Trung has published extensively in top-tier venues like NIPS, ICLR, and JMLR, with over 100 outputs since 2009. His recent work emphasizes robustness in AI systems, including projects on adversarial defense and ethical concept erasure in generative models.
Dr. Weitong Chen is a Senior Lecturer at the School of Computer and Mathematical Sciences, University of Adelaide, and an ARC EC Industry Fellow at the Australian Institute for Machine Learning (AIML). He holds a PhD from the University of Queensland (2020), with prior roles as a Post-Doc Research Fellow and Associate Lecturer there. His research focuses on machine learning applications in medical data, particularly time-series analysis, semi-supervised learning, and IoT. He collaborates widely across academia, industry, and government, supported by multiple grants. His work emphasizes healthcare applications, adversarial robustness, federated learning, and unlearning mechanisms. Education: PhD in Machine Learning, University of Queensland (2020) Master's Degree, University of Queensland Bachelor's Degree, Griffith University Research Interests: Medical Data Analysis (e.g., EHRs, radiology) Time-Series Modeling (healthcare IoT, irregular data) Adversarial Machine Learning (backdoor attacks, robustness) Federated Learning (modality incompleteness, clustered frameworks) Data Privacy (unlearning, compliance) Grants & Collaborations: ARC EC Industry Fellowship Industry partnerships in healthcare and IoT Labs/Teams: Australian Institute for Machine Learning (AIML) Cross-disciplinary health tech collaborations
Professor Xiaohui Tao is a distinguished academic at the University of Southern Queensland's School of Mathematics, Physics and Computing, leading the Computing Discipline Team and chairing the ICT Programs Governance Committee. He holds a PhD in Information Technology from Queensland University of Technology (2009). His research focuses on artificial intelligence, machine learning, and health informatics, with over 200 publications in top journals like IEEE TKDE and conferences such as AAAI and IJCAI. He has mentored 10 doctoral students and leads a research group developing real-world AI applications. Education: PhD in Information Technology, Queensland University of Technology, 2009 Research Interests: Dr. Tao's work spans AI-driven health informatics, machine learning algorithms, natural language processing, and privacy-preserving technologies. His projects address critical challenges like mental health monitoring, smart healthcare systems, and privacy in 5G/IoT environments. Recent advancements include federated learning for unlearning mechanisms and multimodal fusion for medical decision support. Grants & Awards: Awarded Australia Research Council grants (DP220101360), Australian Endeavour Fellowships, and multiple best paper awards at conferences like BESC’22 and WI-IAT’20. Recognized for contributions to remote patient monitoring and AI in depression treatment. Labs & Teams: Leads a research group focused on AI applications in healthcare and data science, collaborating on projects like computational social science for mental health and privacy-preserving IoT systems.
Nan Sun is a Lecturer at the School of Systems & Computing , University of New South Wales, Canberra , conducting interdisciplinary research at the intersection of cybersecurity and artificial intelligence. Her work focuses on data-driven cybersecurity incident prediction, cybersecurity awareness education systems, and AI applications for threat intelligence. PhD in Information Technology (Deakin University) Former Research Fellow at Deakin University's Centre for Cyber Security Research and Innovation Her research spans cybersecurity (60%), machine learning (25%), and software engineering (15%). Recent publications analyze adversarial machine learning, tropical cyclone forecasting with deep learning, and ethical AI frameworks for cyberbullying mitigation. She leads grants including the UNSW Recruitment Research Proposal Grant and CSIRO Data61 funding. Current teaching includes Big Data and Decision Analytics for Security and Digital Forensics . She offers PhD scholarships to students with high academic achievement.
Professor Alan Wee-Chung Liew serves as Head of School at Griffith University's School of Information and Communication Technology, Australia. He joined Griffith University in 2007 after holding positions as Assistant Professor at Chinese University of Hong Kong and Senior Research Fellow at City University of Hong Kong. Professor Liew's research spans Artificial Intelligence, Machine Learning, Medical Imaging, Computer Vision, and Bioinformatics . His work focuses on developing AI solutions for healthcare applications, image analysis, and pattern recognition problems. He leads methodological innovations in machine learning algorithms while maintaining strong connections to real-world applications. His recent publications demonstrate a clear trend toward interdisciplinary AI applications, particularly in medical imaging, healthcare analytics, and trustworthy AI systems. The research shows increasing focus on explainability, privacy preservation, and practical deployment of AI solutions in critical domains. Professor Liew has received significant recognition including: Fellow of the Queensland Academy of Arts and Sciences Fellow of the Australia Computer Society Senior member of IEEE (USA) Stanford University's World's Top 2% Scientists (Computer Science: AI & Image Processing) He actively supervises numerous PhD students across diverse AI topics including medical imaging, graph neural networks, and trustworthy AI. His research is supported by substantial funding from government agencies including ARC, NHMRC, and international collaborations. Professor Liew co-leads the AI4Health lab and the TrustAGI lab , which focus on developing ethical, reliable, and safe AI technologies with strong industry and hospital partnerships.
