A comprehensive review on detection of cyber-attacks: Data sets, methods, challenges, and future research directions

Ahmetoglu, Huseyin; Daş, Resul

doi:10.1016/j.iot.2022.100615

Cited by 35 publications

(15 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The uncovering and classi cation of abnormalities in network events is becoming increasingly di cult due to the rise in complexity and frequency of cyber attacks. Research [17] provided comprehensive tables including the classi cation types utilised in these investigations, the techniques that were compare to previous methods, the routine criteria use, and the outcomes. Study [18] presented a technique that uses the Fuzzy Min Max Neural Networks-Based Intrusion Detection System (FMMNN-IDS) to detect intrusions using deep learning.…”

Section: Related Workmentioning

confidence: 99%

A Robust Deep-learning System for Detecting and Classifying Cyber-attacks in Cloud Computing

2024

Preprint

View full text Add to dashboard Cite

The Internet of Things (IoT) has emerged as the benchmark for low-power lossy networks (LLNs) due to the rapid proliferation of low-power, high-throughput technology. Still, IoT systems are open to cyber attacks because the base devices have limited computing, storage, and communication capabilities. As people rely more and more on cloud computers to store and handle important data, cyber dangers that target cloud settings have become more complex and widespread. The identification and categorization of harmful network activity is crucial in safeguarding the integrity and protection of these systems. Here, we present the full design and implementation of a deep-learning-based system called Enhanced battle royal optimized convolutional neural network (EBRO-CNN) for detecting and classifying cyber attacks in cloud-based telecommunications systems. This optimization method creates tiers for network traffic data depending on characteristics of the cloud. Each layer undergoes its own analysis and optimization to meet its own requirements. This optimization across tiers not only increases detection precision but also makes the system more scalable and flexible in the face of ever-changing cloud workloads. We used the NSL-KDD dataset, which contains demonstrations of all the major cloud computing threats, to gauge the effectiveness of the solution we designed. With an accuracy of up to 99% in various configurations, the findings show that the suggested distributed architecture is useful for detecting various cyber attacks.

show abstract

Section: Related Workmentioning

confidence: 99%

A Robust Deep-learning System for Detecting and Classifying Cyber-attacks in Cloud Computing

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Unfortunately, this has also led to an unprecedented surge in cyberattacks, as criminals develop new and sophisticated methods to exploit vulnerabilities. With businesses and organizations in all sectors adopting technology, it is becoming increasingly difficult to detect and prevent these attacks, presenting a significant challenge to cybersecurity efforts [3][4][5]. The dynamic and intricate nature of these threats presents an escalating challenge for traditional cybersecurity methods to keep pace.…”

Section: Introductionmentioning

confidence: 99%

Knowledge graph reasoning for cyber attack detection

Gilliard,

Liu,

Aliyu

2024

IET Communications

View full text Add to dashboard Cite

In today's digital landscape, cybercriminals are constantly evolving their tactics, making it challenging for traditional cybersecurity methods to keep up. To address this issue, this study explores the potential of knowledge graph reasoning as a more adaptable and sophisticated approach to identify and counter network attacks. By leveraging graph structures imbued with human‐like thinking, this method enhances the resilience of cybersecurity systems. The study focuses on three critical aspects: data preparation, semantic foundations, and knowledge graph inference techniques. Through an in‐depth analysis of these components, the research aims to reveal how knowledge graph reasoning can improve cyberattack detection and enhance the overall efficacy of cybersecurity measures, including intrusion detection systems. The proposed approach has undergone extensive experimentation to validate its effectiveness compared to existing methods. The results of the experiment have shown a remarkable advancement in accuracy, speed, and recall for recognition, surpassing current methods. This achievement is a notable contribution in the realm of managing big data in cybersecurity. The study establishes a foundation for the automation of network attack detection, ultimately enhancing overall network security.

show abstract

“…As more of our lives continue to move online, the need for network security keeps increasing. In recent years, access to computer systems has risen dramatically and intruders have found several ways to hide their identities with ease [15]. Clubbed with the growth of heterogeneous computer networks, these factors have made the problem of intrusion detection quite difficult.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Feature Engineering Based Intrusion Detection System for IoT Network Security

Sadhwani,

Sriwast,

Muthalagu

et al. 2024

Preprint

View full text Add to dashboard Cite

Internet-of-Things (IoT) helps create smart systems by allowing physical environments to be controlled or monitored by users through extensive sensor networks. Such networks are heavily resource constrained due to the low processing power and decentralized placement of sensors. Having been implemented in several backbone sectors such as industry, healthcare, etc, they often deal with sensitive information. Thus, there is an imminent need to secure IoT networks using lightweight intrusion detection systems. To this end, existing works that use BiLSTM for network intrusion detection are explored. Experiments involving the UNSW-NB15 dataset are recreated, and the results are compared. Early stopping is implemented to improve model performance and enable better analysis of the results. Finally, a novel machine learning and feature engineering-based intelligent network intrusion detection framework, dubbed FEIIDS, is proposed. Its working is explained in depth and its time complexity is analyzed. It is tested on the UNSW-NB15 dataset and found to be competitive with existing works, achieving classification accuracies up to 98.8%. Discussions on the results reveal that FEIIDS is more stable, transparent, and lightweight than deep learning models. In fact, FEIIDS can process 2,032,038 records of the dataset in 280.44 seconds, whereas BiLSTM requires 1901.2 seconds to process just 14,000 records. A case study on FEIIDS’s real-world application is also presented. Finally, it is concluded that FEIIDS is highly suitable for use as a real-time intrusion detection system in resource-constrained IoT networks, and its possible future applications are listed.

show abstract

A comprehensive review on detection of cyber-attacks: Data sets, methods, challenges, and future research directions

Cited by 35 publications

References 81 publications

A Robust Deep-learning System for Detecting and Classifying Cyber-attacks in Cloud Computing

A Robust Deep-learning System for Detecting and Classifying Cyber-attacks in Cloud Computing

Knowledge graph reasoning for cyber attack detection

Intelligent Feature Engineering Based Intrusion Detection System for IoT Network Security

Contact Info

Product

Resources

About