A Lightweight Hardware-Friendly CNN Accelerator Security Reinforcement Method

Convolutional neural networks (CNNs), as an important branch of artificial intelligence, have a wide range of applications in security-critical scenarios, and their hardware accelerators are also constantly evolving. However, hardware failures can cause parameter bit flipping, and carefully designed bit-flipping attacks (BFAs) can also severely degrade their classification accuracy. This paper proposes a hardware-friendly security-reinforcement framework, which utilizes the representation characteristics of floating-point numbers on memory units to propose modulation and demodulation reinforcement methods for weights. On the computing unit, a data-threshold constraint reinforcement method is proposed, and a bounded ReLU is introduced to mitigate the impact of BFAs by imposing an upper bound on the activation function. Experimental results demonstrate that when the BER reaches 10−2, the accuracies of LeNet-5, LeNet-3D, and ResNet-18 increase from 13.17%, 12.01%, and 10% to 93.21%, 59.12%, and 62.37%, respectively.