Paper Accepted @PPAI23
The paper titled On Achieving Privacy-Preserving State-of-the-Art Edge Intelligence by Daphnee Chabal, Dolly Sapra, and Zoltan Mann was accepted at 4th AAAI Workshop on Privacy-Preserving Artificial Intelligence.
Deep Neural Networks (DNNs) Inference in Edge Computing, often coined Edge Intelligence, requires solutions to insure that sensitive data confidentiality and intellectual property are not revealed in the process. Privacy-preserving Edge Intelligence is only emerging, despite the growing prevalence of Edge Computing as a context of Machine-Learning-as-a-Service. Solutions have yet to be applied to state-of-the-art DNNs. This position paper provides an original assessment of the compatibility of existing techniques for privacy-preserving DNN Inference with the characteristics of an Edge Computing setup. The resulting favorite candidate is secret sharing. We then address the future role of model compression methods in the research towards secret sharing on DNNs with state-of-the-art performance.