A Semi-Supervised Learning Approach to IEEE 802.11 Network Anomaly Detection

Ran, Jing; Ji, Yidong; Tang, Bihua

doi:10.1109/vtcspring.2019.8746576

Cited by 42 publications

(29 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, this study proposed a hybrid feature selection approach, which incorporates genetic search technique, rule-based engine, and CfsSubsetEval. A subset evaluator figures correlation among all attributes and classes [75]. The attribute-class relationship with a stronger correlation is more likely to be chosen, referred to as feature assessment.…”

Section: Feature Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Feature Selection and Ensemble-Based Intrusion Detection System: An Efficient and Comprehensive Approach

Jaw

Wang

2021

Symmetry

View full text Add to dashboard Cite

The emergence of ground-breaking technologies such as artificial intelligence, cloud computing, big data powered by the Internet, and its highly valued real-world applications consisting of symmetric and asymmetric data distributions, has significantly changed our lives in many positive aspects. However, it equally comes with the current catastrophic daily escalating cyberattacks. Thus, raising the need for researchers to harness the innovative strengths of machine learning to design and implement intrusion detection systems (IDSs) to help mitigate these unfortunate cyber threats. Nevertheless, trustworthy and effective IDSs is a challenge due to low accuracy engendered by vast, irrelevant, and redundant features; inept detection of all types of novel attacks by individual machine learning classifiers; costly and faulty use of labeled training datasets cum significant false alarm rates (FAR) and the excessive model building and testing time. Therefore, this paper proposed a promising hybrid feature selection (HFS) with an ensemble classifier, which efficiently selects relevant features and provides consistent attack classification. Initially, we harness the various strengths of CfsSubsetEval, genetic search, and a rule-based engine to effectively select subsets of features with high correlation, which considerably reduced the model complexity and enhanced the generalization of learning algorithms, both of which are symmetry learning attributes. Moreover, using a voting method and average of probabilities, we present an ensemble classifier that used K-means, One-Class SVM, DBSCAN, and Expectation-Maximization, abbreviated (KODE) as an enhanced classifier that consistently classifies the asymmetric probability distributions between malicious and normal instances. HFS-KODE achieves remarkable results using 10-fold cross-validation, CIC-IDS2017, NSL-KDD, and UNSW-NB15 datasets and various metrics. For example, it outclassed all the selected individual classification methods, cutting-edge feature selection, and some current IDSs techniques with an excellent performance accuracy of 99.99%, 99.73%, and 99.997%, and a detection rate of 99.75%, 96.64%, and 99.93% for CIC-IDS2017, NSL-KDD, and UNSW-NB15, respectively based on only 11, 8, 13 selected relevant features from the above datasets. Finally, considering the drastically reduced FAR and time, coupled with no need for labeled datasets, it is self-evident that HFS-KODE proves to have a remarkable performance compared to many current approaches.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

“…Similarly, it also enables the efficient identification of the predictive ability of every available feature within the dataset. Nevertheless, the factor of redundancy among features plays a significant role in this method [62,75].…”

Section: Cfssubsetevalmentioning

confidence: 99%

Feature Selection and Ensemble-Based Intrusion Detection System: An Efficient and Comprehensive Approach

Jaw

Wang

2021

Symmetry

View full text Add to dashboard Cite

show abstract

“…Similar effort is seen in [23] which proposed a ladder network-based intrusion detection system. However, there is no comparison with supervised counterparts and no mention of feature selection algorithms used.…”

Section: Related Workmentioning

confidence: 66%

“…The performance of 4 variants of autoencoders, based on their reconstruction loss and variance in weights are compared. The Autoencoder AE, only minimizes reconstruction loss which might lead to overfitting [23] during classification. To address this problem, regularization terms are introduced, that provide additional information in the calculation of the loss function.…”

Section: Autoencoder-based Feature Selectionmentioning

confidence: 99%

A New Combined Model with Reduced Label Dependency for Malware Classification

Ray¹,

Nandan²,

Anne³

et al. 2021

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

With the technological advancements in recent times, security threats caused by malware are increasing with no bounds. The first step performed by security analysts for the detection and mitigation of malware is its classification. This paper aims to classify network intrusion malware using new-age machine learning techniques with reduced label dependency and identifies the most effective combination of feature selection and classification technique for this purpose. The proposed model, L2 Regularized Autoencoder Enabled Ladder Networks Classifier (RAELN-Classifier), is developed based on a combinatory analysis of various feature selection techniques like FSFC, variants of autoencoders and semisupervised classification techniques such as ladder networks. The model is trained and tested over UNSW-NB15 and benchmark NSL-KDD datasets for accurate real time model performance evaluation using overall accuracy as well as per-class accuracy and was found to result in higher accuracy compared to similar baseline and state-of-the-art models.

show abstract

“…Shone et al [7] constructed a deep autoencoder (NDAE) for unsupervised feature learning and using stacked NDAEs for intrusion detection. Ran et al [8] provided a semi-supervised learning framework to learn from anomaly traffic. Yan et al [9] designed an LSTM-based model with autoencoders for intrusion detection.…”

Section: Introductionmentioning

confidence: 99%

Voting-Based Ensemble Model for Network Anomaly Detection

Yang

Lin

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Network anomaly detection (NAD) aims to capture potential abnormal behaviors by observing traffic data over a period of time. In this work, we propose a machine learning framework based on XGBoost and deep neural networks to classify normal traffic and anomalous traffic. Data-driven feature engineering and post-processing are further proposed to improve the performance of the models. The experiment results suggest the proposed model can achieve 94% for F1 measure in the macro average of five labels on real-world traffic data.

show abstract

A Semi-Supervised Learning Approach to IEEE 802.11 Network Anomaly Detection

Cited by 42 publications

References 8 publications

Feature Selection and Ensemble-Based Intrusion Detection System: An Efficient and Comprehensive Approach

Feature Selection and Ensemble-Based Intrusion Detection System: An Efficient and Comprehensive Approach

A New Combined Model with Reduced Label Dependency for Malware Classification

Voting-Based Ensemble Model for Network Anomaly Detection

Contact Info

Product

Resources

About