Training robust anomaly detection using ML-Enhanced simulations
This addresses the challenge of sparse edge conditions in anomaly detection for applications like security or monitoring, though it is incremental as it builds on existing simulation and neural network methods.
The paper tackles the problem of anomaly detection systems failing to transition from simulated to real-world data due to simulations being 'too clean', by using neural networks trained on real-world data to enhance simulations for more realistic outputs, resulting in improved training for robust anomaly detection.
This paper describes the use of neural networks to enhance simulations for subsequent training of anomaly-detection systems. Simulations can provide edge conditions for anomaly detection which may be sparse or non-existent in real-world data. Simulations suffer, however, by producing data that is "too clean" resulting in anomaly detection systems that cannot transition from simulated data to actual conditions. Our approach enhances simulations using neural networks trained on real-world data to create outputs that are more realistic and variable than traditional simulations.