Analysis of intrusion detection in cyber attacks using DEEP learning neural networks

Parasuraman, Kumar; Kumar, Avinash; Sahayakingsly, C.; Udayakumar, A.

doi:10.1007/s12083-020-00999-y

Cited by 33 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lezzi et al (2018) demonstrated that effective cybersecurity practices decrease the threat of cyberattacks and protect systems from unauthorized access. Scholars (McCormac et al, 2017; Kumar et al, 2021) emphasized that the organizations' technological capabilities alone are not enough to secure strong cybersecurity systems; developing technical human resource skills through education and training is essential to establishing robust organizational security.…”

Section: Research Model and Hypotheses Developmentmentioning

confidence: 99%

“…Addae et al (2016) proposed a behavioral cybersecurity model based on behavioral theories to identify factors affecting the individuals' cybersecurity behavior. Kumar et al (2021) used the human-organization-technology (HOT) theory as a means by which to identify the drivers required to enrich cybersecurity at the organizational level. The HOT theory was initially designed for the analysis of health information systems (Yusof et al, 2008).…”

Section: Theoretical Backgroundmentioning

confidence: 99%

“…Despite the high stakes and increasing interest public organizations have in cybersecurity risk management, there is minimal knowledge about the drivers of improved cybersecurity levels within organizations especially in developing countries (Kumar et al, 2021; Muller, 2015). Given this gap, this study will empirically investigate the drivers of organizational cybersecurity enhancement.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigating the drivers of cybersecurity enhancement in public organizations: The case of Jordan

Al-Ma’aitah

2022

E J Info Sys Dev Countries

View full text Add to dashboard Cite

Electronic government systems are broadly recognized in the modern era as useful and valid means of delivering e-services. As the importance and prevalence of egovernment services have grown, increasing attention has necessarily been placed on the cybersecurity of electronic programs. Multiple drivers have been identified as contributing to the enhancement of cybersecurity, however, there is limited empirical research confirming these drivers. The main aims of this study are to investigate the drivers of e-government cybersecurity enhancement and determine the impact of cybersecurity on the effectiveness of e-government systems. The study constructs were extracted from the human-organization-technology (HOT) theory and institutional theory. A total of 500 questionnaires were randomly distributed to information technology department staff members and e-government officials in Jordanian ministries. The resulting data were analyzed using a structural equation modeling approach. The findings indicate that technical measures, the role of senior management, coercive pressures, and memetic pressures are important drivers for enhanced cybersecurity levels in governmental organizations. The results also show that enhancing cybersecurity levels in organizations promote the effectiveness of e-government services. These conclusions offer researchers and practitioners insight as to the drivers of an enhanced cybersecurity and the importance of cybersecurity in e-government as a whole.

show abstract

Section: Research Model and Hypotheses Developmentmentioning

confidence: 99%

Section: Theoretical Backgroundmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigating the drivers of cybersecurity enhancement in public organizations: The case of Jordan

Al-Ma’aitah

2022

E J Info Sys Dev Countries

View full text Add to dashboard Cite

show abstract

“…Alotaibi and Alotaibi proposed an abnormal traffic detection method based on a deep neural network, which can identify the normal or abnormal connections in the network, and the detection effect is good [11]. Kumar et al proposed a deep neural network ID system based on context LSTM (Long Short-term Memory Networks) [12]. Firstly, the original data is obtained by social media on the internet, from which the push-level bots are detected, and then the context features are extracted and detected by LSTM.…”

Section: Id System Researchmentioning

confidence: 99%

“…To achieve the desired e ect, we simply need to set and adjust the parameters of the particle system according to the characteristics of special e ects during the development process. e time it takes to write and develop code can be cut in half while achieving special e ects, and good results have been obtained [12].…”

Section: Scene Modelingmentioning

confidence: 99%

Simulation Training Auxiliary Model Based on Neural Network and Virtual Reality Technology

Liu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Training simulators have been gradually evolving in the direction of software, virtualization, networking, and multiplatform in recent years, with the continuous development of hardware and software technologies, particularly the maturity of VR (Virtual Reality) related technologies. The network intrusion program allows remote hackers to take control of the system, posing a serious threat to the network and computer security. As a result, this paper proposes a VR-based ID (intrusion detection) simulation training system. This paper proposes an ID model based on CNN (Convolutional Neural Networks) and LSTM to address these issues (Long Short-term Memory Networks). This model oversamples data from unbalanced data sets, reducing the difference in category data and thus improving the ID model’s performance and existing detection methods to compensate for the flaw. 3DSMAX technology is used to simulate the process visualization scene, as well as some key equipment models and signal transmission simulations, during the system design and implementation process. The experimental results show that CNN LSTM outperforms BP, and the overall evaluation index F1 has significantly improved, particularly the F1 index of D4. CNN LSTM outperforms GA (genetic algorithm) by 12.75 percent and BP by 14.07 percent. The system essentially accomplishes the anticipated simulation training goal, and the simulation training effect is impressive.

show abstract

An Overview of Explainable Artificial Intelligence for Cyber Security

Khoulimi

Limam

Benammar

2022

Studies in Computational Intelligence

View full text Add to dashboard Cite

Analysis of intrusion detection in cyber attacks using DEEP learning neural networks

Cited by 33 publications

References 29 publications

Investigating the drivers of cybersecurity enhancement in public organizations: The case of Jordan

Investigating the drivers of cybersecurity enhancement in public organizations: The case of Jordan

Simulation Training Auxiliary Model Based on Neural Network and Virtual Reality Technology

An Overview of Explainable Artificial Intelligence for Cyber Security

Contact Info

Product

Resources

About