English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Intrusion detection for computer network systems has been becoming one of themost critical tasks for network administrators today. It has an important rolefor organizations, governments and our society due to the valuable resourceshosted on computer networks. Traditional misuse detection strategies are unableto detect new and unknown intrusion types. In contrast, anomaly detection innetwork security aims to distinguish between illegal or malicious events andnormal behavior of network systems. Anomaly detection can be considered as aclassification problem where it builds models of normal network behavior, ofwhich it uses to detect new patterns that significantly deviate from the model.Most of the current approaches on anomaly detection is based on the learning ofnormal behavior and anomalous actions. They do not include memory that is theydo not take into account previous events classify new ones. In this paper, wepropose a one class collective anomaly detection model based on neural networklearning. Normally a Long Short Term Memory Recurrent Neural Network (LSTM RNN)is trained only on normal data, and it is capable of predicting several timesteps ahead of an input. In our approach, a LSTM RNN is trained on normal timeseries data before performing a prediction for each time step. Instead ofconsidering each time-step separately, the observation of prediction errorsfrom a certain number of time-steps is now proposed as a new idea for detectingcollective anomalies. The prediction errors of a certain number of the latesttime-steps above a threshold will indicate a collective anomaly. The model isevaluated on a time series version of the KDD 1999 dataset. The experimentsdemonstrate that the proposed model is capable to detect collective anomalyefficiently

One-class Collective Anomaly Detection based on Long Short-Term Memory Recurrent Neural Networks