Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learning
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition
Rethinking Contrastive Learning in Session-based Recommendation
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
Subgraph Gaussian Embedding Contrast for Self-Supervised Graph Representation Learning
CellCLAT: Preserving Topology and Trimming Redundancy in Self-Supervised Cellular Contrastive Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.