An intrusion detection system for wireless sensor networks using deep neural network

Gowdhaman, V.; Dhanapal, R.

doi:10.1007/s00500-021-06473-y

Cited by 42 publications

(19 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parameters such as precision and recall are comparatively shown in Figure 7. The results of existing methods are obtained from the previous work which was based on a Deep Neural Network (DNN) 25 . From the observations, it is clear that the presented optimized model performs better than the existing models.…”

Section: Resultsmentioning

confidence: 99%

“…Instead of selecting all the features, high‐ranked features are selected and processed to detect the intrusions. Though the presented approach improved the detection rate, it is not accurate since the minimum ranked features also produce some impacts in the intrusions 25–27 …”

Section: Related Workmentioning

confidence: 96%

“…Though the presented approach improved the detection rate, it is not accurate since the minimum ranked features also produce some impacts in the intrusions. [25][26][27] The intrusion detection system presented in Mora-Gimeno et al 28 utilized graphs and neural networks to detect network attacks. System call graph and deep neural network models were integrated to define the data structure and to detect intrusions.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Optimized deep learning‐based intrusion detection for wireless sensor networks

Vembu

Ramasamy

2022

Int J Communication

View full text Add to dashboard Cite

Summary The technological innovations and wide use of Wireless Sensor Network (WSN) applications need to handle diverse data. These huge data possess network security issues as intrusions that cannot be neglected or ignored. An effective strategy to counteract security issues in WSN can be achieved through the Intrusion Detection System (IDS). IDS ensures network integrity, availability, and confidentiality by detecting different attacks. Regardless of efforts by various researchers, the domain is still open to obtain an IDS with improved detection accuracy with minimum false alarms to detect intrusions. Machine learning models are deployed as IDS, but their potential solutions need to be improved in terms of detection accuracy. The neural network performance depends on feature selection, and hence, it is essential to bring an efficient feature selection model for better performance. An optimized deep learning model has been presented to detect different types of attacks in WSN. Instead of the conventional parameter selection procedure for Convolutional Neural Network (CNN) architecture, a nature‐inspired whale optimization algorithm is included to optimize the CNN parameters such as kernel size, feature map count, padding, and pooling type. These optimized features greatly improved the intrusion detection accuracy compared to Deep Neural network (DNN), Random Forest (RF), and Decision Tree (DT) models.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Optimized deep learning‐based intrusion detection for wireless sensor networks

Vembu

Ramasamy

2022

Int J Communication

View full text Add to dashboard Cite

show abstract

“…The second section is devoted to the research on security enhancement. This section includes 8 research contributions, which discusses about: developing a secured and efficient data storage scheme for processing unstructured data in a hybrid cloud/edge environment (Vulapula and Valiveti 2022); proposing an accurate and complete approach for detecting and preventing assaults in cloud computing environment by utilizing both supervised and un-supervised machine learning techniques (Arunkumar and Ashok Kumar 2022); developing and deploying an intrusion detection system to detect cyber-physical attacks in the SCADA system by concatenating the convolutional neural network [CNN] and gated recurrent unit [GRU] as a collective approach (Diaba et al 2022); developing a novel intrusion detection system based on deep neural network (DNN) to find intrusions (Gowdhaman and Dhanapal 2021); proposing a modified device key generation algorithm (MDKGA) algorithm for establishing a secure communication between source and destination based on the QoS parameters (Gayathri et al 2021); proposing a f-slip model to address various attacks such as background knowledge attack, multiple sensitive attribute correlation attack, quasi-identifier correlation attack, non-membership correlation attack and membership correlation attack in 1:M dataset and the solutions for the attacks (Jayapradha and Prakash 2021); applying deep learning models to adaptively learn the attacks and classify them with higher accuracy (Jayabalan and Pugazendi 2021); and utilizing a novel Gaussian mixture design background subtraction methodology to detect objects mainly for enhancing the security of a provide cloud data center (Dhaya et al 2021).…”

Section: Editorialmentioning

confidence: 99%

Special issue on soft computing for edge-driven applications

Chen

Haoxiang

2022

Soft Comput

View full text Add to dashboard Cite

“…An anomaly detection system detects by computing the deviations. Many attacks create a similar profile like normal nodes that show minimum deviation or zero deviation [9]. Many malicious samples are like normal samples.…”

Section: Introductionmentioning

confidence: 99%

AI/ML driven intrusion detection framework for IoT-enabled cold storage monitoring system

Prasad

Pal

Tripathi

et al. 2022

Preprint

View full text Add to dashboard Cite

An IoT-based monitoring system remotely controls and manages intelligent environments. Deployed sensors communicate themselves and transmit data over wireless communication. A sensor node (insider or outsider) is in the communication range, which can send data to other nodes. Due to such nature, it is more vulnerable to intrusions or attacks. Traditional (threshold based) is not powerful enough to detect intrusions, it shows low detection accuracy. An intrusion detection system is an efficient mechanism to detect malicious traffics and prevents abnormal activities. This paper suggests an intrusion detection framework for the cold storage monitoring system. In this, the temperature affects the environment and harms stored products. A malicious node work as a false data injection attack that manipulates temperature and forwards manipulated data, whereas a flooding attack disturbs the existing network. To handle these attacks, a dataset is generated and collected for training the machine learning techniques. Two machine learning techniques have applied as supervised learning (Bayesian Rough Set) and unsupervised learning (micro-clustering). These intrusion detection methods perform better and show high performance. Moreover, this work also provides the comparative analysis of the generated dataset to other IDS datasets.

show abstract

An intrusion detection system for wireless sensor networks using deep neural network

Cited by 42 publications

References 23 publications

Optimized deep learning‐based intrusion detection for wireless sensor networks

Optimized deep learning‐based intrusion detection for wireless sensor networks

Special issue on soft computing for edge-driven applications

AI/ML driven intrusion detection framework for IoT-enabled cold storage monitoring system

Contact Info

Product

Resources

About