Q-Learning for Securing Cyber-Physical Systems : A survey

Alabadi, Montdher; Albayrak, Zafer

doi:10.1109/hora49412.2020.9152841

Cited by 15 publications

(4 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We opted for Q-Learning due to its ability to learn the optimal policy for decision-making based on the observed A. Hidouri, H. Touati, M. Hadded, N. Hajlaoui, P. Muhlethaler, S. Bouzefrane: Preprint submitted to ElsevierPage 7 of 28 system state. In the case of CPA detection, this means that Q-Learning can learn the best strategy for identifying malicious interests based on observed network traffic patterns (52). This ability to learn from experience and adjust the policy accordingly makes Q-Learning an attractive choice for CPA detection.…”

Section: The Proposed Cpa Detection Schemementioning

confidence: 99%

Q-ICAN: A Q-learning based cache pollution attack mitigation approach for named data networking

Hidouri,

Touati,

Hadded

et al. 2023

Computer Networks

View full text Add to dashboard Cite

Section: The Proposed Cpa Detection Schemementioning

confidence: 99%

Q-ICAN: A Q-learning based cache pollution attack mitigation approach for named data networking

Hidouri,

Touati,

Hadded

et al. 2023

Computer Networks

View full text Add to dashboard Cite

“…[15,19,35,54,178] Focus on Network-based IDS. [11] Focus on Reinforcement Learning (RL) based Q-learning methods for securing CPS. [216] Focus on SCADA specific intrusion detection and prevention.…”

Section: Collection Of Articlesmentioning

confidence: 99%

“…The network-based IDS was surveyed in [15,19,35,54,178], but the authors do not address the scenario which differs from conventional networks. A survey reported in [11] focuses on reinforcement learning based Q-Learning method for securing a CPS. The survey focused on CPS in terms of supported techniques, domains, and attacks.…”

Section: Related Surveysmentioning

confidence: 99%

Machine learning for intrusion detection in industrial control systems: Applications, challenges, and recommendations

Umer

Junejo²,

Jilani

et al. 2022

International Journal of Critical Infrastructure Protection

View full text Add to dashboard Cite

“…Artificial intelligence and machine learning methods are used in anomaly-based detection systems. Machine learning methods perform reinforcement, supervised and unsupervised learning to build models (Alabadi, &Albayrak, 2020). These methods are usually preferred in implementations where there is a small amount of data (Baykara, & Daş, 2019).…”

Section: Introductionmentioning

confidence: 99%

Network Intrusion Detection Approach Based on Convolutional Neural Network

Altunay¹,

Albayrak²

2021

European Journal of Science and Technology

Self Cite

View full text Add to dashboard Cite

The probability of encountering cyber-attacks increases with the proliferation of internet usage and the increase in the number of network devices. Intrusion detection systems are used in order to prevent the damages caused by cyber-attacks. In this study, an intrusion detection implementation based on feature selection was performed by using a convolutional neural network in order to prevent cyber-attacks. CSE-CIC-IDS2018 dataset was used during the training and testing stages. Attributes of the dataset were trained on the preprocessing layer, classification layer, and two-layer convolutional neural network. The implementation performance was assessed through accuracy, precision, and recall metrics. A retraining stage was performed in order to resolve the over-learning problem of the network. Intrusion detection was performed through synthetic data generation within the dataset. SMOTE (Synthetic Minority Over Sampling Technique) was used for synthetic data generation. In the study, Brute Force, SQL Injection, Botnet, and DoS attacks were selected as the types of threat. Attack detection accuracy of the intrusion detection system was found 98.32% and the detection accuracy obtained after retraining was found 98.8%. Following the training performed with synthetic data added into the dataset, the neural network carried out a binary classification of the data. The performance rate of detection and classification of the data as a threat was determined as 98.7% for Brute Force, 98.5% for DoS, 98.9% for Botnet, and 99.1% for SQL Injection.

show abstract

Q-Learning for Securing Cyber-Physical Systems : A survey

Cited by 15 publications

References 59 publications

Q-ICAN: A Q-learning based cache pollution attack mitigation approach for named data networking

Q-ICAN: A Q-learning based cache pollution attack mitigation approach for named data networking

Machine learning for intrusion detection in industrial control systems: Applications, challenges, and recommendations

Network Intrusion Detection Approach Based on Convolutional Neural Network

Contact Info

Product

Resources

About