Securing Deep Neural Networks on Edge from Membership Inference Attacks Using Trusted Execution Environments.
,
,
,
,
,
,
,
,
,
,
Proceedings of the 29th ACM/IEEE International Symposium on Low Power Electronics and Design, 2024
An automated approach for improving the inference latency and energy efficiency of pretrained CNNs by removing irrelevant pixels with focused convolutions.
Proceedings of the 29th Asia and South Pacific Design Automation Conference, 2024
An automated approach for improving the inference latency and energy efficiency of pretrained CNNs by removing irrelevant pixels with focused convolutions.
CoRR, 2023