TracInAD: Measuring Influence for Anomaly Detection

Abstract

As with many other tasks, neural networks prove very effective for anomaly detection purposes. However, very few deep-learning models are suited for detecting anomalies on tabular datasets. This paper proposes a novel methodology to flag anomalies based on TracIn, an influence measure initially introduced for explicability purposes. The proposed methods can serve to augment any unsupervised deep anomaly detection method. We test our approach using Variational Autoencoders and show that the average influence of a subsample of training points on a test point can serve as a proxy for abnormality. Our model proves to be competitive in comparison with state-of-the-art approaches: it achieves comparable or better performance in terms of detection accuracy on medical and cyber-security tabular benchmark data.

References in corpus (8)

• Auto-Encoding Variational Bayes
• Understanding Black-box Predictions via Influence Functions
• A Unifying Review of Deep and Shallow Anomaly Detection
• Estimating Training Data Influence by Tracing Gradient Descent
• Learning and Evaluating Representations for Deep One-class Classification
• Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification
• Neural Transformation Learning for Deep Anomaly Detection Beyond Images
• Understanding Instance-based Interpretability of Variational Auto-Encoders

Cited by in corpus (2)

• Training Data Influence Analysis and Estimation: A Survey
• Beyond Individual Input for Deep Anomaly Detection on Tabular Data