Hybrid Deep Neural Network Model for Detection of Security Attacks in IoT Enabled Environment

Sagu, Amit; Gill, Nasib Singh; Gulia, Preeti

doi:10.14569/ijacsa.2022.0130115

Cited by 12 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNN-DBN hybrid classifiers are recommended. CNN and DBN are weight-optimized for detection accuracy by SAEHO [11]. This work developed VANET security and sybil attack detection.…”

Section: Literature Surveymentioning

confidence: 99%

Advanced DDos Attack Detection in SD-IoT Using DNFN and Nature-Inspired Optimizations

Kumbhar Kalpana

2024

jes

View full text Add to dashboard Cite

The purpose of this research is to improve the detection of Distributed Denial of Service (DDoS) attacks in systems that employ Software-Defined Internet of Things (SD-IoT). First, feature selection techniques such as PCA is used to improve the Deep Neuro Fuzzy Network (DNFN) model's detection accuracy of DDoS assaults. With an overall accuracy of 0.969, the findings show that the DNFN model has above average accuracy rates when applied to feature selection technique. To further improve the DDoS detection capabilities, optimization approaches like Elephant Herding Optimization (EHO) and the hybrid Elephant-Herding-Water-Cycle-Algorithm (EHWCA) are then developed. The EHWCA approach is superior than the current EHO method, as shown by a comparative study that compares the two. The DNFN model achieves an accuracy of 0.99 when optimized using EHWCA, whereas it only achieves 0.97 with EHO. The suggested system's scalability and efficiency are greatly enhanced by the inclusion of the water cycle in the optimization process. Overall, this research contributes to the development of strong cybersecurity solutions for IoT networks by demonstrating the efficacy of sophisticated optimization approaches, in particular EHWCA, in improving the detection of DDoS assaults in SD-IoT settings.

show abstract

“…CNN-DBN hybrid classifiers are recommended. CNN and DBN are weight-optimized for detection accuracy by SAEHO [11]. This work developed VANET security and sybil attack detection.…”

Section: Literature Surveymentioning

confidence: 99%

Advanced DDos Attack Detection in SD-IoT Using DNFN and Nature-Inspired Optimizations

Kumbhar Kalpana

2024

jes

View full text Add to dashboard Cite

show abstract

“…The obtained accuracy was 90.01 % using the NSL-KDD dataset. Sagu et al [26] developed a hybrid NN model for the detection of attacks in IoT. It combines CNN and DBN to detect attacks.…”

Section: Related Workmentioning

confidence: 99%

“…Likewise, the proposed feature selection with classification model is compared with other classifiers such as CNN-BiLSTM [31], CNN-DBN [26] and Auto Encoder with DNN [8] in order to prove the efficiency of the complete system. The results are compared in terms of detection rate and AUC and results are shown in Figures 5-6.…”

Section: Comparative Analysis Of Proposed Attack Detection Model With...mentioning

confidence: 99%

Decision Tree with Pearson Correlation-based Recursive Feature Elimination Model for Attack Detection in IoT Environment

Padmashree¹,

Krishnamoorthi²

2022

ITC

View full text Add to dashboard Cite

The industrial revolution in recent years made massive uses of Internet of Things (IoT) applications like smart cities’ growth. This leads to automation in real-time applications to make human life easier. These IoT-enabled applications, technologies, and communications enhance the quality of life, quality of service, people’s well-being, and operational efficiency. The efficiency of these smart devices may harm the end-users, misuse their sensitive information increase cyber-attacks and threats. This smart city expansion is difficult due to cyber attacks. Consequently, it is needed to develop an efficient system model that can protect IoT devices from attacks and threats. To enhance product safety and security, the IoT-enabled applications should be monitored in real-time. This paper proposed an efficient feature selection with a feature fusion technique for the detection of intruders in IoT. The input IoT data is subjected to preprocessing to enhance the data. From the preprocessed data, the higher-order statistical features are selected using the proposed Decision tree-based Pearson Correlation Recursive Feature Elimination (DT-PCRFE) model. This method efficiently eliminates the redundant and uncorrelated features which will increase resource utilization and reduces the time complexity of the system. Then, the request from IoT devices is converted into word embedding using the feature fusion model to enhance the system robustness. Finally, a Deep Neural network (DNN) has been used to detect malicious attacks with the selected features. This proposed model experiments with the BoT-IoT dataset and the result shows the proposed model efficiency which outperforms other existing models with the accuracy of 99.2%.

show abstract

“…Technology and network advancements have created a new environment where the Internet of Things (IoT) is flourishing, fostering several positive social and economic changes [1]. The Internet of Things (IoT) are the networked and interconnected systems, devices, applications, and people that process data [2]. The Internet of Things makes it possible for physical objects to communicate with one another and share critical information while also making decisions and completing important tasks.…”

Section: Introductionmentioning

confidence: 99%

Blockchain-Based Secure Localization against Malicious Nodes in IoT-Based Wireless Sensor Networks Using Federated Learning

Gebremariam

Panda

Indu

2023

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Wireless sensor networks are the core of the Internet of Things and are used in healthcare, locations, the military, and security. Threats to the security of wireless sensor networks built on the Internet of Things (IoT-WSNs) can come from a variety of sources. This study proposes secure attack localization and detection in IoT-WSNs to improve security and service delivery. The technique used blockchain-based cascade encryption and trust evaluation in a hierarchical design to generate blockchain trust values before beacon nodes broadcast data to the base station. Simulation results reveal that cascading encryption and feature assessment measure the trust value of nodes by rewarding each other for service provisioning and trust by removing malicious nodes that reduce localization accuracy and quality of service in the network. Federated machine learning improves data security and transmission by merging raw device data and placing malicious threats in the blockchain. Malicious nodes are classified through federated learning. Federated learning combines hybrid random forest, gradient boost, ensemble learning, K -means clustering, and support vector machine approaches to classify harmful nodes via a feature assessment process. Comparing the proposed system to current ones shows an average detection and classification accuracy of 100% for binary and 99.95% for multiclass. This demonstrates that the suggested approach works well for large-scale IoT-WSNs, both in terms of performance and security, when utilizing heterogeneous wireless senor networks for the providing of secure services.

show abstract

Hybrid Deep Neural Network Model for Detection of Security Attacks in IoT Enabled Environment

Cited by 12 publications

References 32 publications

Advanced DDos Attack Detection in SD-IoT Using DNFN and Nature-Inspired Optimizations

Advanced DDos Attack Detection in SD-IoT Using DNFN and Nature-Inspired Optimizations

Decision Tree with Pearson Correlation-based Recursive Feature Elimination Model for Attack Detection in IoT Environment

Blockchain-Based Secure Localization against Malicious Nodes in IoT-Based Wireless Sensor Networks Using Federated Learning

Contact Info

Product

Resources

About