Deep Learning Based Attack Detection in IIoT using Two-Level Intrusion Detection System

Raja, K.; Karthikeyan, K; Abilash, B; Dev, Kapal; Raja, Gunasekaran

doi:10.21203/rs.3.rs-997888/v1

Cited by 4 publications

(4 citation statements)

References 47 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“… True positive (TP): The model correctly identifies anomalies. True negative (TN): The model correctly identifies non‐anomalies. False positive (FP): The model incorrectly detects anomalies. False negative (FN): The model misses actual anomalies. Precision 31 : measures how accurately the model predicts positive samples with lower false positives. It is useful when minimizing false alarms is essential.…”

Section: Evaluation Of Resultsmentioning

confidence: 99%

“…Precision 31 : measures how accurately the model predicts positive samples with lower false positives. It is useful when minimizing false alarms is essential.…”

Section: Evaluation Of Resultsmentioning

confidence: 99%

“…The label encoding method has been adopted to transform the category values into numerical values. In this method, integer values (0, 1, 2) distinguish between different classes; unlike ordinal encoding, it does not presume a preexisting hierarchy among the categories 31 . Table 4 represents the label encoding performed in the original dataset's target class.…”

Section: Proposed Methodologymentioning

confidence: 99%

See 2 more Smart Citations

ADSBAN: Anomaly detection system for body area networks utilizing IoT and machine learning

Siddiqui,

Kalra,

Krishna

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryBody area networks (BANs) play a pivotal role in modern healthcare, enabling real‐time data collection and monitoring of vital patient parameters, thereby empowering healthcare providers to respond swiftly to any serious health conditions. These networks depend on strategically placed sensors on the patient's body to collect important health data. The integrity of this data is really important, as problems with a component can cause doctors to make mistakes that could be life‐threatening. Consequently, developing and evaluating robust anomaly detection methods for BANs is paramount. To address this concern, an anomaly detection system for body area networks (ADSBAN) has been proposed in this article. Different machine learning methods have been tested and implemented to improve the proposed system's performance. These include decision tree, K‐nearest neighbor, logistic regression (LR), random forest, AdaBoost (Adaptive Boosting), and XGBoost (Extreme Gradient Boosting). Further, this framework has been tested with emulated and standard datasets and compared with existing methodologies. The research employs an IoT Flock emulator to replicate BAN conditions and simulate two distinct attack scenarios. Wireshark aids in thoroughly analyzing network traffic, while Python, in conjunction with tools like Keras and Pandas, is instrumental in implementing the ML models. Further, a CIC flowmeter has been utilized to convert the .pcap file format into .CSV file format. Comprehensive evaluation metrics such as precision, recall, accuracy, F1 score, and the Mathew correlation coefficient (MCC) demonstrate the consistent superiority of LR on emulated (i.e., traffic generated through a simulator IoT Flock) and standard datasets (BoT‐IoT). LR shows the highest accuracy of 99.92% on emulated and standard datasets, while XGBoost has the highest average accuracy of 99.92% on standard dataset. This research significantly bolsters the reliability of healthcare data, instilling confidence among healthcare professionals in their decision‐making processes. By safeguarding the integrity of vital health data in BANs, it advances the quality of patient care. It underscores the indispensable role of ML techniques in fortifying the resilience of healthcare systems.

show abstract

Section: Evaluation Of Resultsmentioning

confidence: 99%

“…Precision 31 : measures how accurately the model predicts positive samples with lower false positives. It is useful when minimizing false alarms is essential.…”

Section: Evaluation Of Resultsmentioning

confidence: 99%

Section: Proposed Methodologymentioning

confidence: 99%

See 1 more Smart Citation

ADSBAN: Anomaly detection system for body area networks utilizing IoT and machine learning

Siddiqui,

Kalra,

Krishna

2024

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…The proposed method, on the other hand, incorporated ANN and RF predictions and attained a 99 percent accuracy rate for all the three datasets. A deep learning strategy was used to address another IIOT intrusion detection model by Raja [31]. The Wireless Communications and Mobile Computing proposed DL-TL-NIDS model had two levels of detection.…”

Section: Related Workmentioning

confidence: 99%

Industrial Internet of Things Intrusion Detection Method Using Machine Learning and Optimization Techniques

Gaber

Awotunde

Folorunso

et al. 2023

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The emergence of the Internet of Things (IoT) has witnessed immense growth globally with the use of various devices found in home, transportation, healthcare, and industry. The deployment and implementation of the IoT paradigm in industrial settings lead to the architectural changes of Industrial Automation and Control Systems (IACS) plus the countless connectivity of industrial systems. This resulted in what is referred to as the Industrial Internet of Things (IIoT), which removes the barrier of connecting IACS to isolated conventional ICT platforms. In recent times, the IoT has started hacking our personal lives and not only our world, thus creating a platform for impending IoT cyberattacks. The widespread use of the IoT has created a rich platform for possible IoT cyberattacks. Machine learning (ML) algorithms have been driven solutions to secure wireless communication in IIoT-based systems, and their use in solving various cybersecurity challenges. Therefore, this paper proposes a novel intrusion detection model based on the Particle Swarm Optimization (PSO) and Bat algorithm (BA) for feature selection, and the Random Forest (RF) classifier for the classification of malicious behaviors in IIoT-based network traffic. An IIoT-based cybersecurity dataset, WUSTL-IIOT-2021 Dataset, was used to evaluate the performance of the proposed model using accuracy, recall, precision, and F1-score. The results of the two feature selection were compared to identify the most promising one. The results were compared with other recent state-of-the-art ML and multiobjective algorithms, and the results showed better performance. The RF along with BA classifier had proved to be the best classifier.

show abstract

Blockchain and federated learning-based intrusion detection approaches for edge-enabled industrial IoT networks: a survey

Ali,

Li,

Yousafzai

2024

Ad Hoc Networks

View full text Add to dashboard Cite

Deep Learning Based Attack Detection in IIoT using Two-Level Intrusion Detection System

Cited by 4 publications

References 47 publications

ADSBAN: Anomaly detection system for body area networks utilizing IoT and machine learning

ADSBAN: Anomaly detection system for body area networks utilizing IoT and machine learning

Industrial Internet of Things Intrusion Detection Method Using Machine Learning and Optimization Techniques

Blockchain and federated learning-based intrusion detection approaches for edge-enabled industrial IoT networks: a survey

Contact Info

Product

Resources

About