A Deep LSTM based Approach for Intrusion Detection IoT Devices Network in Smart Home

Azumah, Sylvia Worlali; Elsayed, Nelly; Adewopo, Victor; Zaghloul, Zaghloul Saad; Li, Chengcheng

doi:10.1109/wf-iot51360.2021.9596033

Cited by 23 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model was trained on twelve epochs with an accuracy of 91% on train and 87% on validation data. Figure (5) shows the accuracy of the trained LSTM model on both train and validation data. We compared the performance of the developed model with other related work in predicting cyberthreat and identifying vulnerability exposures using deep web data.…”

Section: Resultsmentioning

confidence: 99%

“…RNN stores information in memory because their current output is dependent on the previous computations. However, the major problem associated with RNNs are vanishing and exploding gradients, LSTMs were designed to overcome the bottlenecks of RNN by introducing new gates which allow better control over the gradient flow and enable better preservation of long-range dependencies [5,6]. The LSTM architecture is different from other deep learning architectures, LSTM model contains the memory cell and gates which are essential to the architecture namely; the input gate, output gate, and the forget gate.…”

Section: Deep Learning Algorithm For Threat Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Algorithm for Threat Detection in Hackers Forum (Deep Web)

Adewopo¹,

Gonen²,

Elsayed³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

In our current society, the inter-connectivity of devices provides easy access for netizens to utilize cyberspace technology for illegal activities. The deep web platform is a consummative ecosystem shielded by boundaries of trust, information sharing, trade-off, and review systems. Domain knowledge is shared among experts in hackers forums which contain indicators of compromise that can be explored for cyberthreat intelligence. Developing tools that can be deployed for threat detection is integral in securing digital communication in cyberspace. In this paper, we addressed the use of TOR relay nodes for anonymizing communications in deep web forums. We propose a novel approach for detecting cyberthreats using a deep learning algorithm Long Short-Term Memory (LSTM). The developed model outperformed the experimental results of other researchers in this problem domain with an accuracy of 94% and precision of 90%. Our model can be easily deployed by organizations in securing digital communications and detection of vulnerability exposure before cyberattack.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Deep Learning Algorithm For Threat Detectionmentioning

confidence: 99%

Deep Learning Algorithm for Threat Detection in Hackers Forum (Deep Web)

Adewopo¹,

Gonen²,

Elsayed³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…An enforced fallback process needs to be in place when a system is not functioning properly and backup measures are necessary to ensure that security systems can recover from failures [19]. Approximately 70% percent of IoT devices can be hacked and securing these devices is important as they improve the quality of life of people through the advancement of technology [23]. Another method to mitigate back-end attacks involves enforcing data integrity, constraints, and other security features that can make it difficult for an intruder to get into the system.…”

Section: Mitigating the Vulnerabilities Of Biometricsmentioning

confidence: 99%

Evaluation of User Perception on Biometric Fingerprint System

Yeboah¹,

Adewopo²,

Azumah³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Biometric systems involve security assurance to make our system highly secured and robust. Nowadays, biometric technology has been fixed into new systems with the aim of enforcing strong privacy and security. Several innovative system have been introduced, and most of them have biometrics installed to protect military bases, banking machines, and other sophisticated systems, such as online tracking systems. Businesses can now focus on their core functions and feel confident about their data security. Despite the benefits and enhancements in security that biometrics offer, there are also some vulnerabilities. This study aimed to investigate the biometric vulnerabilities in a healthcare facility and propose possible countermeasures for biometric system vulnerabilities.

show abstract

“…It is particularly difficult to achieve when emerging technologies, such as the Internet of Things (IoT), are involved. The internet of devices is estimated to grow to 50 billion by 2020 due to its proliferation in many upcoming applications, such as smart cities, smart homes, smart cars, and intelligent industrial systems [ 3 , 4 ]. This growth presents a huge risk to data privacy, integrity, and availability, which may be exploited by malicious actors.…”

Section: Introductionmentioning

confidence: 99%

Intrusion Detection in IoT Using Deep Learning

Banaamah

Ahmad

2022

Sensors

View full text Add to dashboard Cite

Cybersecurity has been widely used in various applications, such as intelligent industrial systems, homes, personal devices, and cars, and has led to innovative developments that continue to face challenges in solving problems related to security methods for IoT devices. Effective security methods, such as deep learning for intrusion detection, have been introduced. Recent research has focused on improving deep learning algorithms for improved security in IoT. This research explores intrusion detection methods implemented using deep learning, compares the performance of different deep learning methods, and identifies the best method for implementing intrusion detection in IoT. This research is conducted using deep learning models based on convolutional neural networks (CNNs), long short-term memory (LSTM), and gated recurrent units (GRUs). A standard dataset for intrusion detection in IoT is considered to evaluate the proposed model. Finally, the empirical results are analyzed and compared with the existing approaches for intrusion detection in IoT. The proposed method seemed to have the highest accuracy compared to the existing methods.

show abstract

A Deep LSTM based Approach for Intrusion Detection IoT Devices Network in Smart Home

Cited by 23 publications

References 26 publications

Deep Learning Algorithm for Threat Detection in Hackers Forum (Deep Web)

Deep Learning Algorithm for Threat Detection in Hackers Forum (Deep Web)

Evaluation of User Perception on Biometric Fingerprint System

Intrusion Detection in IoT Using Deep Learning

Contact Info

Product

Resources

About