11/12/2024 | Press release | Distributed by Public on 11/13/2024 02:42
Summary:
As Australia's artificial intelligence (AI) sector grows, so too does the need for reliable tools to support it and systems that enable greater cybersecurity control.
Thanks to recently announced ARC Linkage 2024 funding of $429,000, Professor Yong Xiang from Deakin University's School of Information Technology will lead an exciting project with fellow Chief Investigator Dr Leo Zhang (Griffith University) and Partner Investigator James Yang (DHCC Australia), exploring how to ensure reliable deployment of deep neural network (DNN) models in machine learning as a service (MLaaS).
As a driving force of AI, machine learning (ML) has been heralded as a key component of the fourth industrial revolution. It's empowered by DNN models, which simulate the complex decision-making power of the human brain. Companies acting as MLaaS providers supply tailored DNN models to users, but there are some roadblocks to undertaking this work securely and sustainably.
Professor Xiang says he and his project collaborators hope to help overcome these barriers by developing innovative access control methods to guarantee secure and flexible DNN model access, building new methods that are robust against transfer learning cyber attacks and piracy, and working on novel model ownership identification methods.
'Our research will contribute to the Australian Government's cybersecurity priorities and will also assist local AI companies to prevent losses associated with unauthorised DNN model use,' he says.
The Australian Research Council (ARC) Linkage Projects scheme provides support for competitive research projects which initiate or develop long term strategic research alliances, bringing together researchers, higher education organisations, and other organisations including industry.
Professor Xiang teaches at the School of Information Technology within the Faculty of Science Engineering and Built Environments and is also the Director of Deakin's Trustworthy Intelligent Computing Lab (TICL). He has published seven authored books, over 270 refereed journal articles and more than 110 conference papers.
The text of this article is licensed under the Creative Commons Attribution (CC BY) 4.0 International license. We'd love for you to share it, so feel free! Please note that images, videos, graphics and logos are not covered by the CC BY license and may not be used without permission from Deakin University or their respective copyright holder. If you have any questions, please contact [email protected].
Thanks for reading! You can find more stories like this at www.deakin.edu.au/research/research-news-and-publications. We ask that Deakin University and individuals are appropriately credited and that you include links back to this website. Quotes in this article can be extracted for other articles provided individuals are appropriately credited and you include a link back to the article URL.