CAD-DA: Controllable Anomaly Detection after Domain Adaptation by Statistical Inference
This addresses the need for reliable anomaly detection in domain-shift scenarios, though it appears incremental as it builds on existing selective inference concepts.
The paper tackles the problem of conducting valid statistical inference for anomaly detection under domain adaptation, proposing CAD-DA to control the probability of misidentifying anomalies at a pre-specified level (e.g., 0.05). The method is evaluated on synthetic and real-world datasets, demonstrating its ability to handle domain adaptation influences.
We propose a novel statistical method for testing the results of anomaly detection (AD) under domain adaptation (DA), which we call CAD-DA -- controllable AD under DA. The distinct advantage of the CAD-DA lies in its ability to control the probability of misidentifying anomalies under a pre-specified level $α$ (e.g., 0.05). The challenge within this DA setting is the necessity to account for the influence of DA to ensure the validity of the inference results. Our solution to this challenge leverages the concept of conditional Selective Inference to handle the impact of DA. To our knowledge, this is the first work capable of conducting a valid statistical inference within the context of DA. We evaluate the performance of the CAD-DA method on both synthetic and real-world datasets.