Why is the Mahalanobis Distance Effective for Anomaly Detection?
This provides insight into neural classifier behavior for anomaly detection, addressing a practical problem in machine learning safety, but is incremental as it builds on existing methods.
The paper analyzes why the Mahalanobis distance-based method achieves state-of-the-art performance in anomaly detection for pre-trained neural classifiers, finding it uses information not useful for classification, and combines it with another method to improve performance and robustness.
The Mahalanobis distance-based confidence score, a recently proposed anomaly detection method for pre-trained neural classifiers, achieves state-of-the-art performance on both out-of-distribution (OoD) and adversarial examples detection. This work analyzes why this method exhibits such strong performance in practical settings while imposing an implausible assumption; namely, that class conditional distributions of pre-trained features have tied covariance. Although the Mahalanobis distance-based method is claimed to be motivated by classification prediction confidence, we find that its superior performance stems from information not useful for classification. This suggests that the reason the Mahalanobis confidence score works so well is mistaken, and makes use of different information from ODIN, another popular OoD detection method based on prediction confidence. This perspective motivates us to combine these two methods, and the combined detector exhibits improved performance and robustness. These findings provide insight into the behavior of neural classifiers in response to anomalous inputs.