Annual Computer Security Applications Conference (ACSAC) 2022

Full Program »

DRAGON: Deep Reinforcement Learning for Autonomous Grid Operation and Attack Detection

As power grids have evolved, IT has become integral to maintaining reliable power. While providing operators improved situational awareness and the ability to rapidly respond to dynamic situations, IT concurrently increases the cyberattack threat surface – as recent grid attacks such as Blackenergy and Crashoverride illustrate. To defend against such attacks, modern power grids require a system that can maintain reliable power during attacks and detect when these attacks occur to allow for a timely response. To help address limitations of prior work, we propose DRAGON– deep reinforcement learning for autonomous grid operation and attack detection, which (i) autonomously learns how to maintain reliable power operations while (ii) simultaneously detecting cyberattacks. We implement DRAGON and evaluate its effectiveness by simulating different attack scenarios on the IEEE 14 bus power transmission system model. Our experimental results show that DRAGON can maintain safe grid operations 225.47% longer than a state-of-the-art autonomous grid operator. Furthermore, on average, our detection method reports a true positive rate of 92.87% and a false positive rate of 11.35%, while also reducing the false negative rate by 63.11% compared to a recent attack detection method.

Matthew Landen
Georgia Institute of Technology

Keywhan Chung
Lawrence Livermore National Laboratory

Moses Ike
Georgia Institute of Technology

Sarah Mackay
Lawrence Livermore National Laboratory

Jean-Paul Watson
Lawrence Livermore National Laboratory

Wenke Lee
Georgia Institute of Technology

Paper (ACM DL)



Powered by OpenConf®
Copyright©2002-2023 Zakon Group LLC