Co-designing Trusted Execution Environment and Model Encryption for Secure High-Performance DNN Inference on FPGAs

AI processing units (APUs) may need to perform isolated execution for the confidentiality of model information and the integrity of execution tasks. Isolated execution of APUs significantly reduces the processing performance, which results in about three times the execution time overhead due to trusted execution environment (TEE) and cryptographic processing for isolated execution according to previous work. In this paper, we propose a high-performance, practical, and general-purpose isolated execution method of APUs by jointly co-designing APU data transfer and model encryption. In the evaluation results, our method can improve the execution time overhead by a factor of 2 or less compared with the previous work.