miscellaneous-1

Network Intrusion Detection

3260 papers • 126 benchmarks • 313 datasets

Network intrusion detection is the task of monitoring network traffic to and from all devices on a network in order to detect computer attacks.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in network-intrusion-detection-1

Trend

Dataset

Best Model

Actions

CICIDS2017

UNSW-NB15

KDD

Libraries

i

Use these libraries to find network-intrusion-detection-1 models and implementations

xuhongzuo/DeepOD

2 papers 275

Datasets

Kitsune Network Attack Dataset

Subtasks

No subtasks available.

Most implemented papers

Deep Anomaly Detection with Deviation Networks

Guansong Pang, Anton van den Hengel, Chunhua Shen•Wed Jul 24 2019

A novel anomaly detection framework and its instantiation that can be trained substantially more data-efficiently and achieves significantly better anomaly scoring than state-of-the-art competing methods is introduced.

415

Content

NB15-Backdoor

SIDD-Image

IoT Network Intrusion Dataset

IoT Benign and Attack Traces

IoT ENVIRONMENT DATASET

UQ NIDS Datasets (FlowMeter Format)

UQ NIDS Datasets

0

Paper Graph

Evaluating Shallow and Deep Neural Networks for Network Intrusion Detection Systems in Cyber Security

R. Vinayakumar, P. Poornachandran, Rahul Vigneswaran, K. Soman•Sat Jun 30 2018

Intrusion detection system (IDS) has become an essential layer in all the latest ICT system due to an urge towards cyber safety in the day-to-day world. Reasons including uncertainty in finding the types of attacks and increased the complexity of advanced cyber attacks, IDS calls for the need of integration of Deep Neural Networks (DNNs). In this paper, DNNs have been utilized to predict the attacks on Network Intrusion Detection System (N-IDS). A DNN with 0.1 rate of learning is applied and is run for 1000 number of epochs and KDDCup-‘99’ dataset has been used for training and benchmarking the network. For comparison purposes, the training is done on the same dataset with several other classical machine learning algorithms and DNN of layers ranging from 1 to 5. The results were compared and concluded that a DNN of 3 layers has superior performance over all the other classical machine learning algorithms.

155 0

Paper Graph

Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection

A. Shabtai, Y. Elovici, Yisroel Mirsky, Tomer Doitshman•Sat Feb 24 2018

Kitsune is presented: a plug and play NIDS which can learn to detect attacks on the local network, without supervision, and in an efficient online manner, and demonstrates that Kitsune can be a practical and economic NIDS.

903 0

Paper Graph

Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection

Huan Liu, Guansong Pang, Longbing Cao, Ling Chen•Tue Jun 12 2018

This paper introduces a ranking model-based framework, called RAMODO, that unifies representation learning and outlier detection to learn low-dimensional representations that are tailored for a state-of-the-art outlier Detection approach - the random distance-based approach.

233 0

Paper Graph

Anomalydae: Dual Autoencoder for Anomaly Detection on Attributed Networks

Haoyi Fan, Fengbin Zhang, Zuoyong Li•Sun Feb 09 2020

A deep joint representation learning framework for anomaly detection through a dual autoencoder (AnomalyDAE), which captures the complex interactions between network structure and node attribute for high-quality embeddings.

223 0

Paper Graph

A Taxonomy of Network Threats and the Effect of Current Datasets on Intrusion Detection Systems

Hanan Hindy, Ethan Bayne, Robert C. Atkinson, C. Tachtatzis, X. Bellekens, David Brosset, A. Seeam•Wed Jun 03 2020

A unique combination of the taxonomy and the analysis of the datasets provided in this manuscript aims to improve the creation of datasets and the collection of real-world data and reflect network threats more accurately within new datasets.

184 0

Paper Graph

Synthesis of a Machine Learning Model for Detecting Computer Attacks Based on the CICIDS2017 Dataset

Максим Николаевич Горюнов, Андрей Георгиевич Мацкевич, Дмитрий Александрович Рыболовлев•Wed Dec 02 2020

The conclusion was made that it is possible to use machine learning methods to detect computer attacks taking into account these limitations.

23 0

Paper Graph

E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT

Mohanad Sarhan, Siamak Layeghy, M. Portmann, Wai Weng Lo, M. Gallagher•Mon Mar 29 2021

This proposal is the first successful, practical, and extensively evaluated approach of applying GNNs on the problem of network intrusion detection for IoT using flow-based data, and outperforms the state-of-the-art in terms of key classification metrics.

318 0

Paper Graph

IoTGeM: Generalizable Models for Behaviour-Based IoT Attack Detection

Kahraman Kostas, Mike Just, M. Lones•Mon Oct 16 2023

IoTGeM is presented, an approach for modeling IoT network attacks that focuses on generalizability, yet also leads to better detection and performance, and an improved rolling window approach for feature extraction, which demonstrates superior generalization compared to traditional flow-based models.

8 0

Paper Graph

Hybrid Isolation Forest - Application to Intrusion Detection

P. Marteau, Saeid Soheily-Khah, Nicolas Béchet•Tue May 09 2017

The resulting Hybrid Isolation Forest (HIF) is evaluated on a synthetic dataset to analyze the effect of the new meta-parameters that are introduced and verify that the addressed limitation of the IF algorithm is effectively overcame.

25 0

Paper Graph

Adding a benchmark result helps the community track progress.