Can I read Adversarial Attacks on Energy Theft Detection on EtoBox?

Adversarial Attacks on Energy Theft Detection by Philip Edze is a document available to read on EtoBox.

What is Adversarial Attacks on Energy Theft Detection about?

This paper addresses the issue of electricity theft, which poses significant challenges for utility companies, and explores the vulnerabilities of energy theft detection (ETD) systems using machine learning, particularly convolutional neural networks (CNN). The authors conduct experiments to evaluate the performance of a CNN-Adaboost ETD model under adversarial attacks, specifically using a novel Adversarial Data Generation Method (ADGM) and the Fast Gradient Sign Method (FGSM), revealing a substantial decr

Author

Philip Edze

Language

EN