Anomaly Detection Based on Critical Paths for Deep Neural Networks

TL;DR

This paper introduces a novel anomaly detection method for deep neural networks that extracts critical paths using genetic algorithms and ensembles their detection results, outperforming existing methods across various anomaly types.

Contribution

The work presents a new approach to extract critical paths from DNNs via genetic evolution and uses ensemble techniques for improved anomaly detection performance.

Findings

Outperforms state-of-the-art anomaly detection methods

Effective across a broad range of anomaly types

High detection accuracy demonstrated in experiments

Abstract

Deep neural networks (DNNs) are notoriously hard to understand and difficult to defend. Extracting representative paths (including the neuron activation values and the connections between neurons) from DNNs using software engineering approaches has recently shown to be a promising approach in interpreting the decision making process of blackbox DNNs, as the extracted paths are often effective in capturing essential features. With this in mind, this work investigates a novel approach that extracts critical paths from DNNs and subsequently applies the extracted paths for the anomaly detection task, based on the observation that outliers and adversarial inputs do not usually induce the same activation pattern on those paths as normal (in-distribution) inputs. In our approach, we first identify critical detection paths via genetic evolution and mutation. Since different paths in a DNN often capture different features for the same target class, we ensemble detection results from multiple paths by integrating random subspace sampling and a voting mechanism. Compared with state-of-the-art methods, our experimental results suggest that our method not only outperforms them, but it is also suitable for the detection of a broad range of anomaly types with high accuracy.