Intrusion Detection in Internet of Things Based Smart Farming Using Hybrid Deep Learning Framework

Kethineni, Keerthi; Pradeepini, G.

doi:10.21203/rs.3.rs-2498495/v1

Cited by 5 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The feasibility of the solution accomplished by the proposed CAh algorithm is evaluated based on MSE defined in equation (33). Termination: The attainment of maximal iteration or the global best solution terminates the iteration of algorithm.…”

Section: Feasibility Of Solutionmentioning

confidence: 99%

“…The dataset utilized for the assessment of proposed intrusion detection mechanism is KDD CUP 99 [30], CICIDS2017 [31], and UNSW-NB15 Existing methods for comparison: The existing federated learning based deep learning methods like CNN [25], Auto-Encoder [27], RNN [25], BiGRU [33], and GhostNet [34] are compared with proposed method to depict the superiority of the proposed model.…”

Section: Description Of Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Intrusion Detection Through Federated Learning With Enhanced Ghost_BiNet and Homomorphic Encryption

ChandraUmakantham,

Gajendran,

Marappan

2024

IEEE Access

View full text Add to dashboard Cite

This research article proposes a federated learning-based intrusion detection methodology that leverages Enhanced Ghost_BiNet, a novel deep learning model, to enhance the security of information sharing and detection accuracy. Federated learning, a privacy-preserving machine learning technique, is utilized to enable multiple entities to collaboratively train a global intrusion detection model without sharing sensitive data. The proposed system first trains local models using Enhanced Ghost_BiNet, which integrates GhostNet and Bidirectional Gated Recurrent Unit (BiGRU). To optimize the model's performance, the Chaotic Chebyshev Artificial Humming Bird (CAh) algorithm is employed. Homomorphic encryption is applied to encrypt the local model updates, enhancing data privacy and security. Server-side aggregation of updates and collaborative optimization are introduced to minimize communication rounds during data aggregation. The results demonstrate that the Enhanced Ghost_BiNet outperforms traditional models like GhostNet, BiGRU, RNN, Auto Encoder, and CNN in terms of accuracy, precision, recall, F-Score, and mean square error (MSE). For instance, the Enhanced Ghost_BiNet achieves an accuracy of 99.24% on the KDD CUP 99 dataset, surpassing the other models by a significant margin. The proposed methodology provides a robust and secure approach to intrusion detection, ensuring the confidentiality of sensitive data while improving detection accuracy.

show abstract

Section: Feasibility Of Solutionmentioning

confidence: 99%

Section: Description Of Datasetmentioning

confidence: 99%

Enhancing Intrusion Detection Through Federated Learning With Enhanced Ghost_BiNet and Homomorphic Encryption

ChandraUmakantham,

Gajendran,

Marappan

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Some of system's low latency as well as limited resources were addressed in work [11]. The author [12] looked into a novel container role-based method to task scheduling method and suggested a novel fog computing-based visualization service for task scheduling. The proposed system can reduce task delay rates and enhance concurrent tasks on fog nodes.…”

Section: Security Enhancement Based Existing Techniquementioning

confidence: 99%

Optimization algorithms in security and privacy-preserving data disturbance for collaborative edge computing social IoT deep learning architectures

Boopathi

Gupta

et al. 2023

Preprint

View full text Add to dashboard Cite

Edge computing (EC) has been viewed as a viable option for addressing cloud computing's shortcomings in supporting Internet-of-Things (IoT) applications as an innovative strategy. However, edge-assisted IoT security requires to be better guaranteed due to the network's instability and increase in attack surfaces. Practice of safeguarding a given network from threats that could compromise its availability is referred to as network security. In addition, we can add that network security must address issues such as unauthorized access to network-accessible resources and even their misuse. This study proposes a novel approach to improving edge computing-based data privacy through secure data transmission and deep learning-based optimization with Internet of Things. Edge network privacy preservation is accomplished through collaborative architecture and hybrid federated sever-based stochastic vector networks. The trust based multiple encryption algorithm is used to secure the transmission of the data after it has been optimized using firefly grey optimization. Throughput, network security analysis, PDR, latency, and energy consumption were all examined as part of the experimental analysis for network data privacy and optimization.

show abstract

Optimization algorithms in security and privacy-preserving data disturbance for collaborative edge computing social IoT deep learning architectures

Boopathi,

Gupta,

Zabeeulla

et al. 2023

Soft Comput

View full text Add to dashboard Cite

Intrusion Detection in Internet of Things Based Smart Farming Using Hybrid Deep Learning Framework

Cited by 5 publications

References 24 publications

Enhancing Intrusion Detection Through Federated Learning With Enhanced Ghost_BiNet and Homomorphic Encryption

Enhancing Intrusion Detection Through Federated Learning With Enhanced Ghost_BiNet and Homomorphic Encryption

Optimization algorithms in security and privacy-preserving data disturbance for collaborative edge computing social IoT deep learning architectures

Optimization algorithms in security and privacy-preserving data disturbance for collaborative edge computing social IoT deep learning architectures

Contact Info

Product

Resources

About