We have developed a technique called Online Discrepancy Test (ODIT) for real-time detection of anomalies in high-dimensional systems. This algorithm is generic and applicable to various contexts as it does not assume specific data types, probability distributions, and anomaly types. It only requires a nominal training set, and achieves asymptotic optimality in terms of minimizing average detection delay for a given false alarm constraint. Due to its multivariate nature, it can quickly and accurately detect challenging anomalies, such as changes in the correlation structure and stealth low -rate cyberattacks. In conjunction with the detection method there is also an effective technique for localizing the anomalous data dimensions.
Performance of ODIT for an Unknown Anomaly Type in all Three Versions