Link-based penalized trust management scheme for preemptive measures to secure the edge-based internet of things networks

Ahmed, Aneeqa; Qureshi, Kashif Naseer; Anwar, Muhammad; Masud, Farhan; Imtiaz, Junaid; Jeon, Gwanggil

doi:10.1007/s11276-022-02948-4

Cited by 7 publications

(23 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is forms a marker of anomaly. Existing researches have explored this capability of autoencoder neural networks and used it in a variety of areas such as manufacturing [20], medical imaging [21] and network anomalies [22].…”

Section: Autoencoder Neural Network Autoencodermentioning

confidence: 99%

Transfer Learning Auto-Encoder Neural Networks for Anomaly Detection of DDoS Generating IoT Devices

Anwar

Shaheen

Gani

2022

Security and Communication Networks

Self Cite

View full text Add to dashboard Cite

Machine Learning based anomaly detection ap- proaches have long training and validation cycles. With IoT devices rapidly proliferating, training anomaly models on a per device basis is impractical. This work explores the “transfer- ability” of a pre-trained autoencoder model across devices of similar and different nature. We hypothesized that devices of similar nature would have similar high level feature character- istics represented by the initial layers of the autoencoder, while the more distinct features are captured by the innermost layer of the neural network. In our experiments, the centre-most layers of autoencoder models were re-trained with limited new data belonging to a different device. Datasets of seven Mirai infected and nine Bashlite infected IoT devices were used; each dataset also included benign records representing un-infected behaviour. We observed that the model’s detection accuracy improved by an average of 9.52% for Mirai and 44.59% for Bashlite. The highest performance improvement of 26.68% and 73.00% was observed when the anomaly model of Ecobee thermostat was tested on other devices before and after transfer learning for Mirai and Bashlite respectively. Additionally, transfer learning took 47.31% and 58.27% less time for Mirai and Bashlite respectively. We further trialed the efficacy of the autoencoder based anomaly model on flow based records of network traffic using the CIC- IDS2017 dataset. It was observed that the model performed best when distinct outliers in the dataset were present, whereas the model failed to perform decently in cases where the malicious activity did not cause significant deviation in network traffic’s footprint.

show abstract

Section: Autoencoder Neural Network Autoencodermentioning

confidence: 99%

Transfer Learning Auto-Encoder Neural Networks for Anomaly Detection of DDoS Generating IoT Devices

Anwar

Shaheen

Gani

2022

Security and Communication Networks

Self Cite

View full text Add to dashboard Cite

show abstract

“…is DDoS attack was carried out using an interconnected device network that was linked to the Internet, as well as a unique malware named "Mirai botnet," which flooded the victim systems with traffic until they surrendered to the stress [10][11][12][13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Prevention Techniques against Distributed Denial of Service Attacks in Heterogeneous Networks: A Systematic Review

Cheema

Tariq

Hafiz

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

The Distributed Denial of Service (DDoS) attack is one of the most critical issues in network security. These sorts of attacks pose a noteworthy danger to the accessibility of network services for their legitimate users by flooding the bandwidth or network service using various infected computer systems. The targeted servers are overwhelmed with malicious packets or connection requests, causing them to slow down or even crash the server operations which results in preventing genuine users from accessing the service. In this paper, we discussed the detailed classification of DDoS attacks and identified attackers’ motivations behind them and their consequences. Further, the DDoS attacks on IoT devices are elaborated based on applications and network layers. A comprehensive literature review has been conducted on cutting-edge defense techniques to defend against such attacks. An in-depth analysis of each mechanism has been carried out to find the optimal solutions. We fairly evaluated the existing defense techniques for DDoS attacks and presented key findings in comparison tables. Furthermore, this paper provides recommendations for future work for new researchers.

show abstract

“…Most techniques [16][17][18][19][20][21] do not emphasize DT and IDT based on true network factors and possess increased communication and computational costs. Hence, PATM [11], CTBET [8] and BTEM [10] are effective for data integrity, using DT and IDT methods considering essential network metrics serving as a foundation for the proposed trust evaluation scheme at edge nodes. This paper attempts to improve the security flaws of these studies and offer optimal robust and more secure solutions than these protocols.…”

Section: Discussion and Findingsmentioning

confidence: 99%

“…Authors in [11], presented the Path Association-based Trust Management (PATM) scheme for the IoT networks. It is a trust management scheme that considers the history of the link in the routing path from source to destination while weighing the trust values of a given node.…”

Section: Related Workmentioning

confidence: 99%

“…To address these issues, there is a requirement to build a safe, resilient, and detection-efficient technique for dealing with malicious nodes in the network against cyber-attacks. Existing trust evaluation and security solutions are not up to the standard to defend against recent internal and external threats because these models are adopted as monitory measures against probable internal/external attacks [8,10,11]. The security-based evaluation approaches must provide dependability and usability.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Security Provision by Using Detection and Prevention Methods to Ensure Trust in Edge-Based Smart City Networks

Iftikhar,

Qureshi,

Altalbe

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

The concept of smart cities is unique where the intelligent information technologies have used to form a heterogeneous with the help of edge and fog networks. Edge Computing (EC) has gained attention due to its distributive nature that brings computing resources closer to user devices for fast data communications. These networks are vulnerable to a variety of cyber threats due open network design and architecture and a lack of trusted computing resources. The Denial of Service (DoS) and Sybil attacks are common in these networks and cause of services degradation. Whereas in a Sybil attack, a node illegitimately claims multiple identities and escalate and launch more attacks in the networks. Identification and detection of malicious nodes and evaluating their trustworthiness is a challenging task. This paper proposes a novel Assertive Trust-based Efficient Technique (ATBET) for edge-based smart city networks by calculating the direct, indirect, penalized and cumulative trust. The trust is evaluated by using packet drop rate and the penalized over the transmission paths. The proposed solution detects the attacks and eliminates the malicious or selfish nodes from edge-based networks. The experiment results are conducted in simulation and compared proposed solution with state or the art solutions in terms of trustworthiness level, latency, packet delivery ratio, and network life span.

show abstract

Link-based penalized trust management scheme for preemptive measures to secure the edge-based internet of things networks

Cited by 7 publications

References 33 publications

Transfer Learning Auto-Encoder Neural Networks for Anomaly Detection of DDoS Generating IoT Devices

Transfer Learning Auto-Encoder Neural Networks for Anomaly Detection of DDoS Generating IoT Devices

Prevention Techniques against Distributed Denial of Service Attacks in Heterogeneous Networks: A Systematic Review

Security Provision by Using Detection and Prevention Methods to Ensure Trust in Edge-Based Smart City Networks

Contact Info

Product

Resources

About