${\text{A}}^3$: Activation Anomaly Analysis

Abstract

Inspired by recent advances in coverage-guided analysis of neural networks, we propose a novel anomaly detection method. We show that the hidden activation values contain information useful to distinguish between normal and anomalous samples. Our approach combines three neural networks in a purely data-driven end-to-end model. Based on the activation values in the target network, the alarm network decides if the given sample is normal. Thanks to the anomaly network, our method even works in strict semi-supervised settings. Strong anomaly detection results are achieved on common data sets surpassing current baseline methods. Our semi-supervised anomaly detection method allows to inspect large amounts of data for anomalies across various applications.

arXiv commentThe first two authors contributed equally to this work

References in corpus (3)

• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems
• DLA: Dense-Layer-Analysis for Adversarial Example Detection

Cited by in corpus (5)

• Semisupervised Anomaly Detection using Support Vector Regression with Quantum Kernel
• Quantile LSTM: A Robust LSTM for Anomaly Detection In Time Series Data
• Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators
• R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
• Anomaly Detection by Recombining Gated Unsupervised Experts