This project gives the related key functions of the following paper:

Jiangnan Li, Yingyuan Yang, and Jinyuan Stella Sun, " SearchFromFree: Adversarial Measurements for Machine Learning-based Energy Theft Detection ", 2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Tempe, Arizona, USA, November 2020

This project does not provides the related dataset due to the copyright issues. If you are interested in this project, you may apply for the dataset from the Irish Social Science Data Archive (ISSDA) and pre-process the raw datasets according to the methods described in the paper. The energyTheft.py script gives the functions to simulated the six energy theft scenarios and is based on the Array structure of Numpy. It is used for synthetic dataset generation.

The project is implemented based on Python 3.5 with TensorFlow and Keras library.