A^3: Activation Anomaly Analysis
share
Inspired by the recent advances in coverage-guided analysis of neural networks (NNs), we propose a novel anomaly detection approach. We show that the hidden activation values in NNs contain information to distinguish between normal and anomalous samples. Common approaches for anomaly detection base the amount of novelty of each data point solely on one single decision variable. We refine this approach by incorporating the entire context of the model. With our data-driven method, we achieve strong anomaly detection results on common baseline data sets, e.g., MNIST and CSE-CIC-IDS2018, purely based on the automatic analysis of the data. Our anomaly detection method allows to easily inspect data across different domains for anomalies without expert knowledge.
READ FULL TEXT