Loading Now

Summary of A Hybrid Indrnnlstm Approach For Real-time Anomaly Detection in Software-defined Networks, by Sajjad Salem et al.


A hybrid IndRNNLSTM approach for real-time anomaly detection in software-defined networks

by Sajjad Salem, Salman Asoudeh

First submitted to arxiv on: 2 Feb 2024

Categories

  • Main: Machine Learning (cs.LG)
  • Secondary: Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
The paper proposes a novel approach for anomaly detection in software-defined networks (SDN) using a combination of IndRNN and LSTM models. By leveraging the strengths of both methods, the proposed algorithm learns dependent and non-dependent features from time-series data, ultimately achieving improved performance. The authors also explore feature selection techniques, including Filter, Wrapper, Embedded, and Autoencoder models, to identify the most relevant features for the task. Experimental results on NSL-KDD data show that the proposed IndRNNLSTM algorithm with Embedded feature selection achieves a mean absolute error (MAE) of 1.22 and root-mean-square error (RMSE) of 9.92.
Low GrooveSquid.com (original content) Low Difficulty Summary
The paper tries to find a better way to spot unusual things in computer networks using a mix of two different machine learning tools, IndRNN and LSTM. This combination helps the model learn both things that happen together and things that don’t. The authors also look at ways to pick the most important features from the data, which helps the model work better. They test their idea on some real-world data and show that it does a pretty good job of finding unusual things in the network.

Keywords

* Artificial intelligence  * Anomaly detection  * Autoencoder  * Feature selection  * Lstm  * Machine learning  * Mae  * Time series