A Constant-Time Implementation Methodology for Activation Functions on Microcontrollers
Researchers have developed a new methodology for implementing activation functions in embedded neural networks that prevents information leakage through timing side channels. This approach ensures consistent execution times across all inputs, regardless of the specific activation function used, by employing techniques like branchless selection and fixed-cost approximations. Tested on an ARM Cortex-M4 platform with common activation functions, the protected implementations achieved identical cycle counts while maintaining high numerical accuracy, offering a practical solution for secure embedded inference. AI
IMPACT Enhances security for embedded AI systems by mitigating timing-based side-channel attacks.