Intrusion Detection Using Deep Belief Network and Probabilistic Neural Network

Zhao, Guangzhen; Zhang, Cuixiao; Zheng, Lijuan

doi:10.1109/cse-euc.2017.119

Cited by 107 publications

(45 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of hidden nodes is selected from PSO and PNN classifies the lower dimensional data. The outcome reveals the proposed DBN-PNN model outperforms regular PCA-PNN, PNN, and DBN-PNN (non-optimized model) [25]. The number of samples present in the dataset is not distributed evenly but still, with the available data, the model is prepared after processing the data.…”

Section: Background Studymentioning

confidence: 98%

Effective Parameter Optimization & Classification using Bat-Inspired Algorithm with Improving NSSA

Mohanraj¹,

Anbu²

2019

IJEAT

View full text Add to dashboard Cite

Network Security is an important aspectin communication-related activities. In recent times, the advent of more sophisticated technologies changed the way the information is being sharedwith everyone in any part of the world.Concurrently, these advancements are mishandled to compromise the end-user devices intentionally to steal their personal information. The number of attacks made on targeted devices is increasing over time. Even though the security mechanisms used to defend the network is enhanced and kept updated periodically, new advanced methods are developed by the intruders to penetrate the system. In order to avoid these discrepancies, effective strategies must be applied to enhance the security measures in the network. In this paper, a machine learning-based approach is proposed to identify the pattern of different categories of attacks made in the past. KDD cup 1999 dataset is accessed to develop this predictive model. Bat optimization algorithm identifies the optimal parameter subset. Supervised machine learning algorithms were employed to train the model from the data to make predictions. The performance of the system is evaluated through evaluation metrics like accuracy, precision and so on. Four classification algorithms were used out of which, gradient boosting model outperformed the benchmarked algorithms and proved its importance on data classification based on the accuracy obtained from this model.

show abstract

Section: Background Studymentioning

confidence: 98%

Effective Parameter Optimization & Classification using Bat-Inspired Algorithm with Improving NSSA

Mohanraj¹,

Anbu²

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…Then, the weight of the softmax layer are learned by labeled data. In attack detection, DBNs are used for both feature extraction and classification [20][21][22].…”

Section: Deep Brief Network (Dbn)mentioning

confidence: 99%

Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey

2019

View full text Add to dashboard Cite

Networks play important roles in modern life, and cyber security has become a vital research area. An intrusion detection system (IDS) which is an important cyber security technique, monitors the state of software and hardware running in the network. Despite decades of development, existing IDSs still face challenges in improving the detection accuracy, reducing the false alarm rate and detecting unknown attacks. To solve the above problems, many researchers have focused on developing IDSs that capitalize on machine learning methods. Machine learning methods can automatically discover the essential differences between normal data and abnormal data with high accuracy. In addition, machine learning methods have strong generalizability, so they are also able to detect unknown attacks. Deep learning is a branch of machine learning, whose performance is remarkable and has become a research hotspot. This survey proposes a taxonomy of IDS that takes data objects as the main dimension to classify and summarize machine learning-based and deep learning-based IDS literature. We believe that this type of taxonomy framework is fit for cyber security researchers. The survey first clarifies the concept and taxonomy of IDSs. Then, the machine learning algorithms frequently used in IDSs, metrics, and benchmark datasets are introduced. Next, combined with the representative literature, we take the proposed taxonomic system as a baseline and explain how to solve key IDS issues with machine learning and deep learning techniques. Finally, challenges and future developments are discussed by reviewing recent representative studies.

show abstract

“…Commonly, network forensic applications have incorporated a number of techniques based on mathematics and machine learning, such as fuzzy logic, naïve bayes classifiers, support vector machines and neural networks [31][32][33][34]. However, contemporary research has proposed deep learning as an alternative as, long training times notwithstanding, deep models tend to outperform other solutions when tasked with processing large volumes of data [35,36,3,14,17].…”

Section: Deep Learning For Tracing and Discovering Threat Behavioursmentioning

confidence: 99%

“…Since IoT devices are designed to be continuously active, collecting traffic from such a network would result in excessive volumes of data. As such, to analyse the collected data, fast and automated methods are employed, with one prominent example being deep learning that is ideal for rapidly scanning large volumes of network data to detect patterns that indicate and attack [14][15][16][17]. However, in order to utilise a deep learning model, it first needs to be trained, which involves selecting hyperparameters, the values of which can greatly affect its performance [18,19].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Network Forensics with Particle Swarm and Deep Learning: The Particle Deep Framework

Koroniotis

Moustafa

2020

7th International Conference on Artificial Intelligence and Applications

View full text Add to dashboard Cite

The popularity of IoT smart things is rising, due to the automation they provide and its effects on productivity. However, it has been proven that IoT devices are vulnerable to both well established and new IoT-specific attack vectors. In this paper, we propose the Particle Deep Framework, a new network forensic framework for IoT networks that utilised Particle Swarm Optimisation to tune the hyperparameters of a deep MLP model and improve its performance. The PDF is trained and validated using Bot-IoT dataset, a contemporary network-traffic dataset that combines normal IoT and non-IoT traffic, with well known botnet-related attacks. Through experimentation, we show that the performance of a deep MLP model is vastly improved, achieving an accuracy of 99.9% and false alarm rate of close to 0%.

show abstract

Intrusion Detection Using Deep Belief Network and Probabilistic Neural Network

Cited by 107 publications

References 9 publications

Effective Parameter Optimization & Classification using Bat-Inspired Algorithm with Improving NSSA

Effective Parameter Optimization & Classification using Bat-Inspired Algorithm with Improving NSSA

Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey

Enhancing Network Forensics with Particle Swarm and Deep Learning: The Particle Deep Framework

Contact Info

Product

Resources

About