SLA${}^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation

Abstract

Anomaly detection is a fundamental yet challenging problem in machine learning due to the lack of label information. In this work, we propose a novel and powerful framework, dubbed as SLA${}^2$P, for unsupervised anomaly detection. After extracting representative embeddings from raw data, we apply random projections to the features and regard features transformed by different projections as belonging to distinct pseudo classes. We then train a classifier network on these transformed features to perform self-supervised learning. Next we add adversarial perturbation to the transformed features to decrease their softmax scores of the predicted labels and design anomaly scores based on the predictive uncertainties of the classifier on these perturbed features. Our motivation is that because of the relatively small number and the decentralized modes of anomalies, 1) the pseudo label classifier's training concentrates more on learning the semantic information of normal data rather than anomalous data; 2) the transformed features of the normal data are more robust to the perturbations than those of the anomalies. Consequently, the perturbed transformed features of anomalies fail to be classified well and accordingly have lower anomaly scores than those of the normal samples. Extensive experiments on image, text and inherently tabular benchmark datasets back up our findings and indicate that SLA${}^2$P achieves state-of-the-art results on unsupervised anomaly detection tasks consistently.

References in corpus (20)

• Scikit-learn: Machine Learning in Python
• Explaining and Harnessing Adversarial Examples
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Deep Learning for Anomaly Detection: A Survey
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• Efficient GAN-Based Anomaly Detection
• Deep Anomaly Detection Using Geometric Transformations
• CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
• Unsupervised Learning by Predicting Noise
• An Overview of Robust Subspace Recovery
• Deep Nearest Neighbor Anomaly Detection
• Classification-Based Anomaly Detection for General Data
• SSD: A Unified Framework for Self-Supervised Outlier Detection
• Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data
• Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
• Robust PCA for Anomaly Detection in Cyber Networks
• Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection
• Are pre-trained CNNs good feature extractors for anomaly detection in surveillance videos?
• Novelty Detection via Robust Variational Autoencoding

Cited by in corpus (1)

• Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook