SNN-IDS: Hardware-Verified SNN-Equivalent Intrusion Detection on a Commodity MCU NPU

First hardware-verified deployment of an INT8 quantized ANN (mathematically equivalent to T=1 SNN inference) for network intrusion detection on the STM32N6570-DK Neural-ART NPU, achieving 0.4561ms inference latency at 800MHz. Includes QCFS activation comparison experiment revealing that the Floor operator falls back to CPU on Neural-ART NPU, confirming ReLU INT8 as the optimal deployment path for SNN-equivalent inference on general-purpose MCU NPUs.

If you use this software, please cite it as below.

Keywords

stm32n6, spiking-neural-network, intrusion-detection-system, int8-quantization, rtos, nsl-kdd, neural-art-npu, edge-ai

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average

Found an issue? Give us feedback

0

Average