Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learning
knowledge discovery and data mining(2024)
摘要
Deep Neural Network (DNN) models when implemented on executing devices as the
inference engines are susceptible to Fault Injection Attacks (FIAs) that
manipulate model parameters to disrupt inference execution with disastrous
performance. This work introduces Contrastive Learning (CL) of visual
representations i.e., a self-supervised learning approach into the deep
learning training and inference pipeline to implement DNN inference engines
with self-resilience under FIAs. Our proposed CL based FIA Detection and
Recovery (CFDR) framework features (i) real-time detection with only a single
batch of testing data and (ii) fast recovery effective even with only a small
amount of unlabeled testing data. Evaluated with the CIFAR-10 dataset on
multiple types of FIAs, our CFDR shows promising detection and recovery
effectiveness.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要