Defense against Joint Poison and Evasion Attacks: A Case Study of DERMS
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909190677594112 |
|---|---|
| author | Abdeen, Zain ul Roy, Padmaksha Al-Tawaha, Ahmad Jia, Rouxi Freeman, Laura Beling, Peter Liu, Chen-Ching Sangiovanni-Vincentelli, Alberto Jin, Ming |
| author_facet | Abdeen, Zain ul Roy, Padmaksha Al-Tawaha, Ahmad Jia, Rouxi Freeman, Laura Beling, Peter Liu, Chen-Ching Sangiovanni-Vincentelli, Alberto Jin, Ming |
| contents | There is an upward trend of deploying distributed energy resource management systems (DERMS) to control modern power grids. However, DERMS controller communication lines are vulnerable to cyberattacks that could potentially impact operational reliability. While a data-driven intrusion detection system (IDS) can potentially thwart attacks during deployment, also known as the evasion attack, the training of the detection algorithm may be corrupted by adversarial data injected into the database, also known as the poisoning attack. In this paper, we propose the first framework of IDS that is robust against joint poisoning and evasion attacks. We formulate the defense mechanism as a bilevel optimization, where the inner and outer levels deal with attacks that occur during training time and testing time, respectively. We verify the robustness of our method on the IEEE-13 bus feeder model against a diverse set of poisoning and evasion attack scenarios. The results indicate that our proposed method outperforms the baseline technique in terms of accuracy, precision, and recall for intrusion detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02989 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Defense against Joint Poison and Evasion Attacks: A Case Study of DERMS Abdeen, Zain ul Roy, Padmaksha Al-Tawaha, Ahmad Jia, Rouxi Freeman, Laura Beling, Peter Liu, Chen-Ching Sangiovanni-Vincentelli, Alberto Jin, Ming Cryptography and Security Systems and Control There is an upward trend of deploying distributed energy resource management systems (DERMS) to control modern power grids. However, DERMS controller communication lines are vulnerable to cyberattacks that could potentially impact operational reliability. While a data-driven intrusion detection system (IDS) can potentially thwart attacks during deployment, also known as the evasion attack, the training of the detection algorithm may be corrupted by adversarial data injected into the database, also known as the poisoning attack. In this paper, we propose the first framework of IDS that is robust against joint poisoning and evasion attacks. We formulate the defense mechanism as a bilevel optimization, where the inner and outer levels deal with attacks that occur during training time and testing time, respectively. We verify the robustness of our method on the IEEE-13 bus feeder model against a diverse set of poisoning and evasion attack scenarios. The results indicate that our proposed method outperforms the baseline technique in terms of accuracy, precision, and recall for intrusion detection. |
| title | Defense against Joint Poison and Evasion Attacks: A Case Study of DERMS |
| topic | Cryptography and Security Systems and Control |
| url | https://arxiv.org/abs/2405.02989 |