RPL Attack Detection and Prevention in the Internet of Things Networks Using a GRU Based Deep Learning

Cakir, Semih; Toklu, Sinan; Yalçin, Nesibe

doi:10.1109/access.2020.3029191

Cited by 67 publications

(40 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The difference of deep learning from ANN is the hidden layers in its structure. Successive layers take the output of the previous layer as input and its structure is based on learning the representation of data [39] [40] [41]. When deep learning techniques are used with very large data, they yield better results than traditional data processing methods [39] [40] [42] [43].…”

Section: Deep Learning Based Car Park Occupancy Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Mobile Application Design for Smart Parking

Canlı

Toklu

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

In the era of Internet of Things (IoT) and smart city ecosystems, there is a need for innovative smart parking systems for more sustainable cities. With the increasing number of vehicles in the cities every year, it takes more time to find parking spaces. The solution methods developed are no longer sufficient. The time that passes while waiting for a parking space in traffic carries with it problems such as energy, environmental pollution and stress. In this study, a deep learning and cloud-based new mobile smart parking application was developed to minimize the problem of searching for parking spaces. Within the application, a service has been developed based on deep learning with Long short-term memory (LSTM) to predict the parking space. Here, dynamic access is provided to the LSTM-based model previously created through the mobile device of the user, and the process of displaying the occupancy rates of the parks at the desired place is accomplished on the mobile device by entering the relevant parameters. By this means, both energy and time savings have been achieved. With the real-time car parking data collected in the city of Istanbul in Turkey, high accuracy results were obtained. In order to demonstrate the effectiveness of the model proposed, it was compared with the Support Vector Machine, Random Forest and ARIMA methods. The results have confirmed the high accuracy and reliability that was promised.

show abstract

Section: Deep Learning Based Car Park Occupancy Predictionmentioning

confidence: 99%

“…The computational complexity of the LSTM is ( 1 ( 2 + 0 )), where 1 is the number of features in inputs, is the number of the hidden units, and 0 is the number of outputs [41]. The computational complexity of operations performed in Jupiter Notebook has been computed as O (n).…”

Section: Figure 6 Flow Diagram Of Proposed Modelmentioning

confidence: 99%

Deep Learning-Based Mobile Application Design for Smart Parking

Canlı

Toklu

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Though many works proposed various IDS for IoT networks, only few literatures proposed IDS for RPL based IoT networks. Cakir et al [10] presented a deep-leaning-based gated recurrent unit (GRU) to detect hello flooding (HF) attacks with high accuracy rate in the RPL based IoT networks. They have compared the performance measures of proposed model with SVM and LR classifiers.…”

Section: Ids In Rpl Based Iotmentioning

confidence: 99%

“…These algorithms train a classifier with normal and anomaly data for attack detection in IoT network. Many literature works on IDSs are focused on different classification techniques like ML classifier [8,9], deep learning classifiers [10,11], or ensemble learning [12,13]. Of this, ensemble learning combines multiple classifiers to make better classification with reduced FPR compared to individual classifiers.…”

Section: Introductionmentioning

confidence: 99%

A Novel Intrusion Detection System for RPL Based IoT Networks with Bio-Inspired Feature Selection and Ensemble Classifier

Prakash

2021

Preprint

View full text Add to dashboard Cite

Internet of Things (IoT) is the powerful latest trend that allows communications and networking of many sources over the internet. Routing protocol for low power and lossy networks (RPL) based IoT networks may be exposed to many routing attacks due to resource-constrained and open nature of the IoT nodes. Hence, there is a need for network intrusion detection system (NIDS) to protect RPL based IoT networks from routing attacks. The existing techniques for anomaly-based NIDS (ANIDS) subjects to high false alarm rate (FAR). Therefore, a novel bio-inspired voting ensemble classifier with feature selection technique is proposed in this paper to improve the performance of ANIDS for RPL based IoT networks. The proposed voting ensemble classifier combines the results of various base classifiers such as logistic Regression, support vector machine, decision tree, bidirectional long short-term memory and K-nearest neighbor to detect the attacks accurately based on majority voting rule. The optimized weights of base classifiers are obtained by using the feature selection method called simulated annealing based improved salp swarm algorithm (SA-ISSA), which is the hybridization of particle swarm optimization, opposition based learning and salp swarm algorithm. The experiments are performed with RPL-NIDDS17 dataset that contains seven types of attack instances. The performance of the proposed model is evaluated and compared with existing feature selection and classification techniques in terms of accuracy, attack detection rate (ADR), FAR and so on. The proposed ensemble classifier shows better performance with higher accuracy (96.4%), ADR (97.7%) and reduced FAR (3.6%).

show abstract

“…In that sense, the incorporation of Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), and Reinforcement Learning (RL) sensors has become imperative to deal with large amounts of samples, maximize feature engineering, learn from latent abnormal patterns, reduce the time for disclosing unknown vulnerabilities, and reinforce classification outcomes [ 19 ]. Despite this, AI-enhanced and semi-enhanced frameworks are more oriented towards easing flooding attacks [ 19 , 20 ], wormhole attacks [ 21 ], machine-driven hello-flood attacks [ 22 ], Received Signal Strength Indicator (RSSI) flooding attacks [ 23 ], and DDoS attacks [ 24 ], leaving Cloning ID attacks as a virtually unexplored area of research. In this work, we present a novel protection framework based on unsupervised ML pre-processing techniques, along with a Dense Neural Network (DNN) approach, to effectively detect counterfeiting attacks on RPL-based network conversations.…”

Section: Introductionmentioning

confidence: 99%

A Dense Neural Network Approach for Detecting Clone ID Attacks on the RPL Protocol of the IoT

Morales-Molina

Hernandez-Suarez

Sánchez-Pérez

et al. 2021

Sensors

View full text Add to dashboard Cite

At present, new data sharing technologies, such as those used in the Internet of Things (IoT) paradigm, are being extensively adopted. For this reason, intelligent security controls have become imperative. According to good practices and security information standards, particularly those regarding security in depth, several defensive layers are required to protect information assets. Within the context of IoT cyber-attacks, it is fundamental to continuously adapt new detection mechanisms for growing IoT threats, specifically for those becoming more sophisticated within mesh networks, such as identity theft and cloning. Therefore, current applications, such as Intrusion Detection Systems (IDS), Intrusion Prevention Systems (IPS), and Security Information and Event Management Systems (SIEM), are becoming inadequate for accurately handling novel security incidents, due to their signature-based detection procedures using the matching and flagging of anomalous patterns. This project focuses on a seldom-investigated identity attack—the Clone ID attack—directed at the Routing Protocol for Low Power and Lossy Networks (RPL), the underlying technology for most IoT devices. Hence, a robust Artificial Intelligence-based protection framework is proposed, in order to tackle major identity impersonation attacks, which classical applications are prone to misidentifying. On this basis, unsupervised pre-training techniques are employed to select key characteristics from RPL network samples. Then, a Dense Neural Network (DNN) is trained to maximize deep feature engineering, with the aim of improving classification results to protect against malicious counterfeiting attempts.

show abstract

RPL Attack Detection and Prevention in the Internet of Things Networks Using a GRU Based Deep Learning

Cited by 67 publications

References 29 publications

Deep Learning-Based Mobile Application Design for Smart Parking

Deep Learning-Based Mobile Application Design for Smart Parking

A Novel Intrusion Detection System for RPL Based IoT Networks with Bio-Inspired Feature Selection and Ensemble Classifier

A Dense Neural Network Approach for Detecting Clone ID Attacks on the RPL Protocol of the IoT

Contact Info

Product

Resources

About