Countering Evasion Attacks for Smart Grid Reinforcement Learning-Based Detectors
Fraudulent customers in smart power grids employ cyber-attacks by manipulating their smart meters and reporting false consumption readings to reduce their bills. To combat these attacks and mitigate financial losses, various machine learning-based electricity theft detectors have been proposed. Unfo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10242112/ |
| _version_ | 1797685370260815872 |
|---|---|
| author | Ahmed T. El-Toukhy Mohamed M. E. A. Mahmoud Atef H. Bondok Mostafa M. Fouda Maazen Alsabaan |
| author_facet | Ahmed T. El-Toukhy Mohamed M. E. A. Mahmoud Atef H. Bondok Mostafa M. Fouda Maazen Alsabaan |
| author_sort | Ahmed T. El-Toukhy |
| collection | DOAJ |
| description | Fraudulent customers in smart power grids employ cyber-attacks by manipulating their smart meters and reporting false consumption readings to reduce their bills. To combat these attacks and mitigate financial losses, various machine learning-based electricity theft detectors have been proposed. Unfortunately, these detectors are vulnerable to serious cyber-attacks, specifically evasion attacks. The objective of this paper is to investigate the robustness of deep reinforcement learning (DRL)-based detectors against our proposed evasion attacks through a series of experiments. Firstly, we introduce DRL-based electricity theft detectors implemented using the double deep Q networks (DDQN) algorithm. Secondly, we propose a DRL-based attack model to generate adversarial evasion attacks in a black box attack scenario. These evasion samples are generated by modifying malicious reading samples to deceive the detectors and make them appear as benign samples. We leverage the attractive features of reinforcement learning (RL) to determine optimal actions for modifying the malicious samples. Our DRL-based evasion attack model is compared with an FGSM-based evasion attack model. The experimental results reveal a significant degradation in detector performance due to the DRL-based evasion attack, achieving an attack success rate (ASR) ranging from 92.92% to 99.96%. Thirdly, to counter these attacks and enhance detection robustness, we propose hardened DRL-based defense detectors using an adversarial training process. This process involves retraining the DRL-based detectors on the generated evasion samples. The proposed defense model achieves outstanding detection performance, with a degradation in ASR ranging from 1.80% to 9.20%. Finally, we address the challenge of whether the DRL-based hardened defense model, which has been adversarially trained on DRL-based evasion samples, is capable of defending against FGSM-based evasion samples, and vice versa. We conduct extensive experiments to validate the effectiveness of our proposed attack and defense models. |
| first_indexed | 2024-03-12T00:44:10Z |
| format | Article |
| id | doaj.art-6d72aeb817ee46309bb4ad6e3541a39d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T00:44:10Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6d72aeb817ee46309bb4ad6e3541a39d2023-09-14T23:00:55ZengIEEEIEEE Access2169-35362023-01-0111973739739010.1109/ACCESS.2023.331237610242112Countering Evasion Attacks for Smart Grid Reinforcement Learning-Based DetectorsAhmed T. El-Toukhy0https://orcid.org/0000-0002-7402-2478Mohamed M. E. A. Mahmoud1https://orcid.org/0000-0002-8719-501XAtef H. Bondok2https://orcid.org/0000-0001-6790-8310Mostafa M. Fouda3https://orcid.org/0000-0003-1790-8640Maazen Alsabaan4https://orcid.org/0000-0001-8601-3184Department of Electrical and Computer Engineering, Tennessee Tech University, Cookeville, TN, USADepartment of Electrical and Computer Engineering, Tennessee Tech University, Cookeville, TN, USADepartment of Electrical and Computer Engineering, Tennessee Tech University, Cookeville, TN, USADepartment of Electrical and Computer Engineering, College of Science and Engineering, Idaho State University, Pocatello, ID, USADepartment of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi ArabiaFraudulent customers in smart power grids employ cyber-attacks by manipulating their smart meters and reporting false consumption readings to reduce their bills. To combat these attacks and mitigate financial losses, various machine learning-based electricity theft detectors have been proposed. Unfortunately, these detectors are vulnerable to serious cyber-attacks, specifically evasion attacks. The objective of this paper is to investigate the robustness of deep reinforcement learning (DRL)-based detectors against our proposed evasion attacks through a series of experiments. Firstly, we introduce DRL-based electricity theft detectors implemented using the double deep Q networks (DDQN) algorithm. Secondly, we propose a DRL-based attack model to generate adversarial evasion attacks in a black box attack scenario. These evasion samples are generated by modifying malicious reading samples to deceive the detectors and make them appear as benign samples. We leverage the attractive features of reinforcement learning (RL) to determine optimal actions for modifying the malicious samples. Our DRL-based evasion attack model is compared with an FGSM-based evasion attack model. The experimental results reveal a significant degradation in detector performance due to the DRL-based evasion attack, achieving an attack success rate (ASR) ranging from 92.92% to 99.96%. Thirdly, to counter these attacks and enhance detection robustness, we propose hardened DRL-based defense detectors using an adversarial training process. This process involves retraining the DRL-based detectors on the generated evasion samples. The proposed defense model achieves outstanding detection performance, with a degradation in ASR ranging from 1.80% to 9.20%. Finally, we address the challenge of whether the DRL-based hardened defense model, which has been adversarially trained on DRL-based evasion samples, is capable of defending against FGSM-based evasion samples, and vice versa. We conduct extensive experiments to validate the effectiveness of our proposed attack and defense models.https://ieeexplore.ieee.org/document/10242112/Securityelectricity theftevasion attacksreinforcement learningadversarial trainingsmart power grids |
| spellingShingle | Ahmed T. El-Toukhy Mohamed M. E. A. Mahmoud Atef H. Bondok Mostafa M. Fouda Maazen Alsabaan Countering Evasion Attacks for Smart Grid Reinforcement Learning-Based Detectors IEEE Access Security electricity theft evasion attacks reinforcement learning adversarial training smart power grids |
| title | Countering Evasion Attacks for Smart Grid Reinforcement Learning-Based Detectors |
| title_full | Countering Evasion Attacks for Smart Grid Reinforcement Learning-Based Detectors |
| title_fullStr | Countering Evasion Attacks for Smart Grid Reinforcement Learning-Based Detectors |
| title_full_unstemmed | Countering Evasion Attacks for Smart Grid Reinforcement Learning-Based Detectors |
| title_short | Countering Evasion Attacks for Smart Grid Reinforcement Learning-Based Detectors |
| title_sort | countering evasion attacks for smart grid reinforcement learning based detectors |
| topic | Security electricity theft evasion attacks reinforcement learning adversarial training smart power grids |
| url | https://ieeexplore.ieee.org/document/10242112/ |
| work_keys_str_mv | AT ahmedteltoukhy counteringevasionattacksforsmartgridreinforcementlearningbaseddetectors AT mohamedmeamahmoud counteringevasionattacksforsmartgridreinforcementlearningbaseddetectors AT atefhbondok counteringevasionattacksforsmartgridreinforcementlearningbaseddetectors AT mostafamfouda counteringevasionattacksforsmartgridreinforcementlearningbaseddetectors AT maazenalsabaan counteringevasionattacksforsmartgridreinforcementlearningbaseddetectors |