← 返回 JSSC 论文列表JSSC 2024第9期Clocking & PLLsNeural Network Accelerator
An Energy-Efficient Neural Network Accelerator With Improved Resilience Against
一款具有抗故障攻击能力的能效神经网络加速器ASIC。
高错误检测能力，面积开销5.9%，对NN精度影响可忽略
神经网络加速器抗故障攻击能效ASIC轻量级加密
▸集成轻量级加密校验以检测模型错误
▸作为故障检测传感器识别计算错误
▸高错误检测能力与低面积开销（5.9%）
Abstract
Embedded neural network (NN) implementations
are vulnerable to misclassification under fault attacks (FAs).
Clock glitching and injecting strong electromagnetic (EM) pulses
are two simple yet detrimental FA techniques that disrupt
the NN by: 1) introducing errors in the NN model and
2) corrupting NN computation results. This article introduces
the first application-specific integrated circuit (ASIC) demon-
stration of an energy-efficient NN accelerator equipped with
built-in FA detection capabil