LSTM for Model-Based Anomaly Detection in Cyber-Physical Systems
This addresses anomaly detection for cyber-physical systems, but it is incremental as it builds on existing LSTM methods with minor modifications.
The paper tackled anomaly detection in cyber-physical systems by using LSTM neural networks to model system dynamics and a modified error metric for uncertainty, achieving results analyzed on both artificial and real data.
Anomaly detection is the task of detecting data which differs from the normal behaviour of a system in a given context. In order to approach this problem, data-driven models can be learned to predict current or future observations. Oftentimes, anomalous behaviour depends on the internal dynamics of the system and looks normal in a static context. To address this problem, the model should also operate depending on state. Long Short-Term Memory (LSTM) neural networks have been shown to be particularly useful to learn time sequences with varying length of temporal dependencies and are therefore an interesting general purpose approach to learn the behaviour of arbitrarily complex Cyber-Physical Systems. In order to perform anomaly detection, we slightly modify the standard norm 2 error to incorporate an estimate of model uncertainty. We analyse the approach on artificial and real data.