An Algorithm for Out-Of-Distribution Attack to Neural Network Encoder

2020/09/17 by Liang Liang, Liang, Liang, Linhai Ma +5
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2009.08016

openalex publication_date 2020/09/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Making machine learning robust against adversarial inputs
• 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
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples

Related

• Robust Image Classification in the Presence of Out-of-Distribution and Adversarial Samples Using Attractors in Neural Networks
• Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output
• Provably Robust Detection of Out-of-distribution Data (almost) for free
• Model2Detector: Widening the Information Bottleneck for Out-of-Distribution Detection using a Handful of Gradient Steps
• Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection