AR-Pro: CounterfactualExplanationsforAnomaly RepairwithFormalProperties

Anomaly detection is widely used for identifying critical errors and suspicious behaviors, butcurrent methods lackinterpretability. Weleverage common propertiesofexisting methods andrecent advancesingenerativemodels tointroduce counterfactual explanations for anomaly detection. Givenan input, we generate its counterfactual as a diffusion-based repair that shows what a non-anomalous versionshouldhavelookedlike.