Anomaly-Based Intrusion Detection Using Extreme Learning Machine and Aggregation of Network Traffic Statistics in Probability Space

Atli, Buse Gul; Miché, Yoan; Kalliola, Aapo; Oliver, Ian; Holtmanns, Silke; Lendasse, Amaury

doi:10.1007/s12559-018-9564-y

Cited by 52 publications

(27 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Probabilistic-based Methods. Conventional probabilistic methods [12]- [16], [40], [41] model the inliers' features' distributions, where the outliers are detected as samples with low probability. Several approximations to the true distribution of the data have been proposed, for instance, Genetic programming [42] to estimate a kernel density function, minimum-volume-sets to estimate a particular level set of the unknown nominal multivariate density [43], or constructing minimal graphs covering a K-point subset to estimate the critical region [44], [45].…”

Section: Related Workmentioning

confidence: 99%

Anomaly Detection Based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation

Rivera

Khan

Bekkouch

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Anomaly detection suffers from unbalanced data since anomalies are quite rare. Synthetically generated anomalies are a solution to such ill or not fully defined data. However, synthesis requires an expressive representation to guarantee the quality of the generated data. In this paper, we propose a two-level hierarchical latent space representation that distills inliers' feature-descriptors (through autoencoders) into more robust representations based on a variational family of distributions (through a variational autoencoder) for zero-shot anomaly generation. From the learned latent distributions, we select those that lie on the outskirts of the training data as synthetic-outlier generators. And, we synthesize from them, i.e., generate negative samples without seen them before, to train binary classifiers. We found that the use of the proposed hierarchical structure for feature distillation and fusion creates robust and general representations that allow us to synthesize pseudo outlier samples. And in turn, train robust binary classifiers for true outlier detection (without the need for actual outliers during training). We demonstrate the performance of our proposal on several benchmarks for anomaly detection.

show abstract

Section: Related Workmentioning

confidence: 99%

Anomaly Detection Based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation

Rivera

Khan

Bekkouch

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…The use of ELM for IDS was also used with probabilistic algorithms. This is shown in the work of [1], where a probability density function is learned based on flow features for frequent communications. The authors have used a hierarchical heavy hitters' algorithm for clustering network statistics and learning the probability density function of each feature using ELM.…”

Section: Literature Surveymentioning

confidence: 99%

“…Intrusion detection is the task of observing, analysing and identifying activities aiming to violate a network's security policy. The key success factor for identifying such activities relies on an appropriate monitoring of the network by diagnosing its usage chronically [1]. In the past, organisations used specific authentication policies articulating various levels of accessing.…”

Section: Introductionmentioning

confidence: 99%

Intrusion Detection System Based on Gradient Corrected Online Sequential Extreme Learning Machine

2021

View full text Add to dashboard Cite

“…35 Knowledge representation is of great significance to modern science. In many fields, it has been regarded as the main driving force for the application of theory to practice, such as, aggregation, 36 evidence resolution, [37][38][39] decision-making [40][41][42] and so on. [43][44][45] Interestingly, probability is similar to coins, it also has a original side and a negative side.…”

Section: Gini Entropymentioning

confidence: 99%

The generalization negation of probability distribution and its application in target recognition based on sensor fusion

Gao

Deng

2019

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Target recognition in uncertain environments is a hot issue. Fusion rules are used to combine the sensor reports from different sources. In this situation, obtaining more information to make correct decision is an essential issue. Probability distribution is one of the most used methods to represent uncertainty information. In addition, the negation of probability distribution provides a new view to represent the uncertainty information. In this article, the existing negation of probability distribution is extended with Tsallis entropy. The main reason is that different systems have different parameter q. Some numerical examples are used to demonstrate the efficiency of the proposed method. Besides, the article also discusses the application of negation in target recognition based on sensor fusion to further demonstrate the importance of negation.

show abstract

Anomaly-Based Intrusion Detection Using Extreme Learning Machine and Aggregation of Network Traffic Statistics in Probability Space

Cited by 52 publications

References 31 publications

Anomaly Detection Based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation

Anomaly Detection Based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation

Intrusion Detection System Based on Gradient Corrected Online Sequential Extreme Learning Machine

The generalization negation of probability distribution and its application in target recognition based on sensor fusion

Contact Info

Product

Resources

About