NIDS-Network Intrusion Detection System Based on Deep and Machine Learning Frameworks with CICIDS2018 using Cloud Computing

Currently Machine-learning (ML) methods are widely active in this era of information security. Owing to unpredictable actions and unknown vulnerabilities, conventional security strategies based on rules remain vulnerable to sophisticated attacks. ML techniques enable us to develop IDS-Intrusion Dete...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2020 International Conference on Smart Innovations in Design, Environment, Management, Planning and Computing (ICSIDEMPC) S. 27 - 30
Hauptverfasser: Bharati, Manisha Prakash, Tamane, Sharvari
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 30.10.2020
Schlagworte:
Artificial intelligence
AWS
Cloud Computing
CSECIC-IDS2018
Deep Learning
Forestry
Machine learning Models
Neurons
NIDS
Optimization
Organizations
Standards organizations
Training
Vegetation
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Currently Machine-learning (ML) methods are widely active in this era of information security. Owing to unpredictable actions and unknown vulnerabilities, conventional security strategies based on rules remain vulnerable to sophisticated attacks. ML techniques enable us to develop IDS-Intrusion Detection Systems focused upon finding of anomalies rather than detection of misuse. In addition, threshold problems in detecting anomalies can also be overcome by machine-learning. Like the malicious code datasets, there are relatively few data sets for network intrusion detection. KDDCUP-99 remains the dataset most utilized for IDS assessment. Numerous experiments on ML-Machine Learning based IDS utilizing KDD or enhanced KDD models. Dataset CSE-CICIDS-2018, is used in this paper which contains the most cutting-edge basic system threats. We employ an Intrusion Detection System with Machine Learning Based (Random Forest) for CSE-CIC-IDS-2018 provides an exceptional score with Accuracy score 99%.
DOI:10.1109/ICSIDEMPC49020.2020.9299584