On-device machine learning (ML) is rapidly gaining popularity on mobile devices. Mobile developers can use on-device ML to enable ML features at users’ mobile devices, such as face recognition, augmented virtual reality, voice assistance, and medical diagnosis. This new paradigm is further accelerated by AI chips and ASICs embedded on mobile devices, e.g., Apple’s Bionic neural engine. Compared to cloud-based machine learning services, on-device ML is privacy-friendly, of low latency, and can work offline. User data will remain at the mobile device for ML inference.
Problems: In order to enable on-device ML, models must be deployed at the local mobile devices, thereby creating a new attack surface inevitably. Commercial ML models are now stored on mobile devices, which is completely out of the control of the model owners. They can be easily stolen or abused if not properly protected. A recent empirical study [1] has demonstrated that half of on-device ML models are stored in plaintext form at the devices, and even if encryption is used to protect ML models, those models can be extracted during dynamic analysis.
To secure on-device ML models, in this project, we aim to employ privacy-enhancing techniques to design new and efficient algorithms that can provide strong protection during the entire life cycle of ML models used on the devices.
Research Task I: Investigate ML algorithms and optimisations which are friendly to privacy-enhancing techniques and on-device ML, including but not limited to model compression, quantisation, distillation, transfer learning, pruning, etc.
Research Task II: Apply privacy-enhancing techniques such as secure multi-party computation, homomorphic encryption, differential privacy, and trusted execution to design algorithms and protocols to secure ML models within their life cycle at mobile devices.
Research Task III: Conduct theoretical and experimental analysis for the performance of the proposed designs as well as the security against attacks on on-device ML.
Impact: The outcome of this project will directly contribute to the roadmap of securely developing on-device ML applications and systems, i.e., preventing capital loss of companies and protecting the data of data owners and end-users involved in on-device training and inference. The outcome is of excellent commercialisation value given the increasing popularity of on-device applications using ML models for decision making.
[1] Sun et al., "Mind your weight(s): A large-scale study on insufficient machine learning model protection in mobile apps.", USENIX Security, 2021.
Similar Positions
-
Associate Dean (Interaction, Technology & Information), RMIT University, Australia, about 10 hours ago
Overview: A leadership opportunity is available in the newly established Discipline of Interaction, Technology & Information in the School of Computing Technologies. 1 x Full time, fixed term (3 y...
-
Property Business Partner, RMIT University, Australia, about 10 hours ago
Overview: Are you passionate about connecting with people and making a meaningful impact? We are looking for a Dynamic Property Business Partner position who is passionate, determined, and enthusi...
-
Wil Administration Officer (Guss), RMIT University, Australia, 17 days ago
Overview: • Administrative Services Officer, commencing as soon as possible. • Hybrid ways of working • Based at the Melbourne CBD Campus About RMIT RMIT offers life-changing experiences ...
-
Solutions Architect Genomics Machine Learning, CSIRO, Australia, 1 day ago
Lead the technical development of the VariantSpark platform and clinical pathology applications Use your cloud-based, high-performance computing & machine learning expertise to bring IT solut...
-
Education Technologist, University of Melbourne, Australia, 4 days ago
Job no: 0062174 Location: Parkville Role type: Full-time, Fixed-term for 2 years Faculty: Faculty of Medicine, Dentistry and Health Sciences Department/School: Department of Anatomy and Physiology...
-
Lecturer (Midwifery), Australian Catholic University, Australia, 17 days ago
Campus Location: Melbourne, Australia Job No: APTAV101046#012 Deliver high quality teaching and learning outcomes through the development, delivery and continuous improvement of midwifery curricul...