← Search

Oleg Sokolsky

2 accepted papers

2024

AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties

NeurIPS 2024poster

Anomaly detection is widely used for identifying critical errors and suspicious behaviors, but current methods lack interpretability. We leverage common properties of existing methods and recent advances in generative models to introduce counterfactual explanations for anomaly detection. Given an in…

2022

iDECODe: In-Distribution Equivariance for Conformal Out-of-Distribution Detection

AAAI 2022technical

Machine learning methods such as deep neural networks (DNNs), despite their success across different domains, are known to often generate incorrect predictions with high confidence on inputs outside their training distribution. The deployment of DNNs in safety-critical domains requires detection of…