Intrusion Detection System using Deep Neural Networks (DNN)

Navya, V; Adithi, J; Rudrawal, Diksha; Tailor, Harshita; James, Nileena

doi:10.1109/icaeca52838.2021.9675513

Cited by 12 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another important area where deep learning has been applied is in anomaly detection for identifying network faults. Navya et al [34] proposed a deep learning-based method for detecting network anomalies and achieved a high precision in their results. Furthermore, Naseer et al [35] utilized a deep residual learning network for intrusion detection in wireless sensor networks, achieving higher accuracy over baseline methods.…”

Section: Related Workmentioning

confidence: 99%

Root Cause Analysis of Communication Network Based on Deep Fuzzy Neural Network

Zhang

2023

IEEE Access

View full text Add to dashboard Cite

In the realm of communication networks, root cause analysis plays a vital role in maintaining efficient and reliable operation. However, existing root cause analysis methods face limitations and drawbacks, including their inability to handle complex data and disturbances, as well as inaccuracies in identifying root causes. To this end, we present the Deep Fuzzy Neural Network approach as an innovative solution.Integrating the strengths of deep learning and fuzzy logic inference, where the deep learning technique utilizes the parallel computing fusion of convolutional neural network and long short-term memory to extract the spatial-temporal features from sophisticated fault data of communication network. By leveraging this parallel computing fusion module, the proposed framework effectively addresses the flaws of traditional root cause analysis methods. Furthermore, the incorporation of fuzzy logic enables our model to manage disturbances such as uncertainty and noise inherent in the data, ensuring robust performance. Experimental results also demonstrate our proposed deep fuzzy neural network approach is an effective method for network root cause analysis in overcoming limitations inherent in existing methods and providing superior accuracy and resilience.

show abstract

Section: Related Workmentioning

confidence: 99%

Root Cause Analysis of Communication Network Based on Deep Fuzzy Neural Network

Zhang

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Traditional DNNs are frequently utilised in attack and threat detection [20]. The deep learning architecture uses many neurons to introduce non-linearity in classification hypotheses, thereby increasing classification complexity.…”

Section: B: Lstmmentioning

confidence: 99%

“…In [20], authors, claim in the paper, that by using DNN, a sort of deep learning model enables the development of a flexible and effective IDS for detecting and classifying unanticipated and unpredictable cyberattacks. However, they did not add simulations to prove their statement, and they do not clearly show the proof of concept.…”

Section: B Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Deep Hierarchical Machine Learning Approach for Identification of Known and Unknown Multiple Security Attacks in a D2D Communications Network

Rani,

Ioannou,

Nagaradjane

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Intrusion Detection Systems (IDSs) have played a crucial role in identifying cyber threats for a very long time. Still, their significance has increased significantly with the advent of 5G/6G technologies, particularly Device-to-Device (D2D) communication. Multiple cyberattacks, such as Man in the Middle (MITM) attacks, Structured Query Language (SQL) injection attacks, Dictionary attacks, Distributed Denial of Service (DDoS) attacks, and others by using specific attack tools such as HULK, RUDY, and GoldenEye, that can cause rapid battery drain, rendering D2D network devices more prone to hardware failure or even to the dissolution of the D2D communication network affecting the operation and the performance of the mobile network. Using a Deep Hierarchical Machine Learning Model/Deep Hierarchical Neural Network (DHMLM/DHNN) technique, we develop an Intrusion Detection System (IDS) for D2D communication that, due to its hierarchical structure, is distinct from other comparable approaches. (i.e., Recurrent Neural Networks (RNN), Deep Neural Networks (DNN), Long short-term memory (LSTM)), has several advantages, including i) reduced training time (training time can be reduced by 56%.); ii) the ability to identify multiple types of attacks; iii) the ability to identify Zero-day/Unknown attacks (i.e., attacks that it has not seen before); iv) a more straightforward model design due to the low number of connections and neurons compared to other approaches (excluding RNN and LSTM), and; v) overall outstanding performance in terms of accuracy (i.e., 99.07%). The custom/unified data set used to train and evaluate the model was partially manually emulated and partially sampled from a large set (>95%) from the commonly used CIC-DDoS-2019 data set. The after-comparison final proposed model's 99.07% accuracy on this unified data set demonstrates the efficacy of our method. The model was also tested and demonstrated an astounding 99.63% accuracy for zero-day/unknown attacks.

show abstract

“…A SIEM system is able to detect harmful behavior while avoiding false positives because it correlates data from several sources and uses advanced techniques of alert filtering. [2] Although there are many more types of intrusion detection systems, two of the most common kinds are network intrusion detection systems (NIDS) and host-based intrusion detection systems (HIDS) (HIDS). Examples of network intrusion detection systems (NIDS) include systems that analyze incoming network traffic, whereas examples of host intrusion detection systems (HIDS) include systems that monitor important operating system files.…”

Section: Introductionmentioning

confidence: 99%

An Artificial Neural Network Technique for Prediction of Cyber-Attack using Intrusion Detection System

Jain¹,

Waoo²

2023

JAIMLNN

View full text Add to dashboard Cite

An intrusion detection system, often known as IDS, is a piece of equipment or a piece of software that monitors a network or collection of devices in order to search for indications of possible intrusion. The frequency of cyber assaults has grown in recent years, and with it, the damage they do to society. The study of cyber security and the avoidance of cyber assaults, such as the use of intrusion detection as a defensive mechanism, is therefore needed. The internet services are widely used. Services based on computers, the internet, and other forms of technology are all considered part of the cyber world. The cyber world has advanced greatly thanks to new protocols and technologies. Cyber security is a major issue for every service that operates online. Network and host-based intrusion detection systems (NIDS/HIDS) are the backbones of any cyber security infrastructure. The NSL-KDD dataset is often used in algorithm research and verification and is widely employed in both the study and development of intrusion detection systems. In this study, we provide a neural network approach to intrusion detection system threat prediction. In this paper, the Python Spyder software is used for the simulation.

show abstract

Intrusion Detection System using Deep Neural Networks (DNN)

Cited by 12 publications

References 3 publications

Root Cause Analysis of Communication Network Based on Deep Fuzzy Neural Network

Root Cause Analysis of Communication Network Based on Deep Fuzzy Neural Network

A Novel Deep Hierarchical Machine Learning Approach for Identification of Known and Unknown Multiple Security Attacks in a D2D Communications Network

An Artificial Neural Network Technique for Prediction of Cyber-Attack using Intrusion Detection System

Contact Info

Product

Resources

About