Investigation of Voltage Fault Injection Attacks on NN Inference Utilizing NVM Based Weight Storage
Supriya Chakraborty, Tamoghno Das, Manan Suri · 2023
This study investigates the vulnerability of Neural Networks (NNs) with weights stored in commercial Non-Volatile Memory (NVM) chips to Voltage Fault Injection (VFI) attack. In particular, we present the vulnerabilities of NOR Flash and Resistive Random Access Memory (ReRAM) chips to VFI attack. We experimentally inject voltage glitches with ~ 12% variation in power supply compared to the data-sheet specifications. As a case study, we implement two NNs: i) Multilayer Perceptron (MLP) and ii) AlexNet (CNN) trained on Fashion MNIST (FMNIST) and CIFAR-10 datasets respectively. We observe failure of read operations in NVM chips due to VFI. The occurrences of soft errors lead to significant corruption (~91% for FMNIST and ~42% for CIFAR-10 datasets) in the trained weights read out. Experimental results show that the inference accuracy of NNs drops to ~10% for FMNIST and ~14.36% for CIFAR-10.