• Corpus ID: 210152524

Anomaly Detection for Cybersecurity: Time Series Forecasting and Deep Learning

@article{Col2020AnomalyDF,
  title={Anomaly Detection for Cybersecurity: Time Series Forecasting and Deep Learning},
  author={Giordano Col{\`o}},
  journal={viXra},
  year={2020}
}
  • G. Colò
  • Published 2020
  • Computer Science
  • viXra
Finding anomalies when dealing with a great amount of data creates issues related to the heterogeneity of different values and to the difficulty of modelling trend data during time. In this paper we combine the classical methods of time series analysis with deep learning techniques, with the aim to improve the forecast when facing time series with long-term dependencies. Starting with forecasting methods and comparing the expected values with the observed ones, we will find anomalies in time… 

Figures from this paper

References

SHOWING 1-7 OF 7 REFERENCES
LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection
TLDR
This work proposes a Long Short Term Memory Networks based Encoder-Decoder scheme for Anomaly Detection (EncDec-AD) that learns to reconstruct 'normal' time-series behavior, and thereafter uses reconstruction error to detect anomalies.
A Multi-Horizon Quantile Recurrent Forecaster
We propose a framework for general probabilistic multi-step time series regression. Specifically, we exploit the expressiveness and temporal nature of Recurrent Neural Networks, the nonparametric
GluonTS: Probabilistic Time Series Models in Python
TLDR
Gluon Time Series is introduced, a library for deep-learning-based time series modeling that provides all necessary components and tools that scientists need for quickly building new models, for efficiently running and analyzing experiments and for evaluating model accuracy.
LSTM: A Search Space Odyssey
TLDR
This paper presents the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling, and observes that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.
Introduction to time series and forecasting
TLDR
A general approach to Time Series Modelling and ModeLLing with ARMA Processes, which describes the development of a Stationary Process in Terms of Infinitely Many Past Values and the Autocorrelation Function.
A multimodal execution monitor with anomaly classification for robot-assisted feeding
TLDR
This work introduces a multimodal execution monitor to detect and classify anomalous executions when robots operate near humans and implemented and evaluated it in the context of robot-assisted feeding with a general-purpose mobile manipulator.