An Empirical Study on Network Anomaly Detection Using Convolutional Neural Networks

Kwon, Donghwoon; Natarajan, Kathiravan; Suh, Sang C.; Kim, Hyun‐Joo; Kim, Jin Oh

doi:10.1109/icdcs.2018.00178

Cited by 113 publications

(71 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The experimental results on the NSLKDD dataset [27] showed that the recurrent neural network model (LSTM) delivers the best performance with 89% of accuracy. Also using CNN, the work presented in [10] used one-dimensional convolutional layers to detect anomaly in networks. Nevertheless, except autoencoders, CNN and LSTM need labeled data for training purposes.…”

Section: Related Workmentioning

confidence: 99%

An Empirical Study on Unsupervised Network Anomaly Detection using Generative Adversarial Networks

Truong-Huu

Dheenadhayalan

Kundu

et al. 2020

Proceedings of the 1st ACM Workshop on Security and Privacy on Artificial Intelligence

View full text Add to dashboard Cite

Network anomalies can arise due to various causes such as abnormal behaviors from users, malfunctioning network devices, malicious activities performed by attackers, malicious software or botnets. With the emergence of machine learning and especially deep learning, many works in the literature developed learning models that are able to detect network anomalies. However, these models require massive amounts of labeled data for model training and may not be able to detect unknown anomalous traffic or zeroday attacks. Unsupervised learning techniques such as autoencoder and its variants do not require labeled data but their performance is still poor. Generative adversarial networks (GANs) have successfully demonstrated their capability of implicitly learning data distributions of arbitrarily complex dimensions. This motivates us to carry out an empirical study on the capability of GANs in network anomaly detection. We adopt two existing GAN models and develop new neural networks for their components, i.e., generator and discriminator. We carry out extensive experiments to evaluate the performance of GANs and compare with existing unsupervised detection techniques. We use multiple datasets that include both realistic traffic captures (PCAP) and synthetic traffic generated by simulation platforms. We develop a traffic aggregation technique to extract statistical features that are useful for the models to learn traffic behaviors. The experimental results show that GANs outperform the existing techniques with a significant improvement in different performance metrics.

show abstract

Section: Related Workmentioning

confidence: 99%

An Empirical Study on Unsupervised Network Anomaly Detection using Generative Adversarial Networks

Truong-Huu

Dheenadhayalan

Kundu

et al. 2020

Proceedings of the 1st ACM Workshop on Security and Privacy on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…The proposed technique facilitates dimensionality reduction of non-symmetric data and it uses random forest as classifier. In [483], the authors have studied the effectiveness of CNN architectures of different depth for NIDS. They have used 3 CNN models of varying depth called shallow, moderate and deep CNN.…”

Section: A Deep Learning In Intrusion Detectionmentioning

confidence: 99%

A Comprehensive Tutorial and Survey of Applications of Deep Learning for Cyber Security

Ravi¹,

Alazab²,

Sriram³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The use of CNNs for network anomaly detection is explored in [28]. The authors show that deep learning is better than shallow learning due to the non-linearity of network data sets.…”

Section: Related Workmentioning

confidence: 99%

SuperB: Superior Behavior-based Anomaly Detection Defining Authorized Users’ Traffic Patterns

Karasek

Kim

Kemmoe

et al. 2020

2020 29th International Conference on Computer Communications and Networks (ICCCN)

View full text Add to dashboard Cite

An Empirical Study on Network Anomaly Detection Using Convolutional Neural Networks

Cited by 113 publications

References 8 publications

An Empirical Study on Unsupervised Network Anomaly Detection using Generative Adversarial Networks

An Empirical Study on Unsupervised Network Anomaly Detection using Generative Adversarial Networks

A Comprehensive Tutorial and Survey of Applications of Deep Learning for Cyber Security

SuperB: Superior Behavior-based Anomaly Detection Defining Authorized Users’ Traffic Patterns

Contact Info

Product

Resources

About