An Algorithm for Out-Of-Distribution Attack to Neural Network Encoder
arXiv:2009.08016
Abstract
Deep neural networks (DNNs), especially convolutional neural networks, have achieved superior performance on image classification tasks. However, such performance is only guaranteed if the input to a trained model is similar to the training samples, i.e., the input follows the probability distribution of the training set. Out-Of-Distribution (OOD) samples do not follow the distribution of training set, and therefore the predicted class labels on OOD samples become meaningless. Classification-based methods have been proposed for OOD detection; however, in this study we show that this type of method has no theoretical guarantee and is practically breakable by our OOD Attack algorithm because of dimensionality reduction in the DNN models. We also show that Glow likelihood-based OOD detection is breakable as well.
arXiv comment26 pages, 25 figures, 8 tables
References in corpus (9)
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Deep Learning for Anomaly Detection: A Survey
- Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
- Deep Anomaly Detection with Outlier Exposure
- WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
- Implicit Generation and Generalization in Energy-Based Models
- Uncertainty in the Variational Information Bottleneck
- Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System