Abstract
|
Current machine learning approaches for ne … Current machine learning approaches for network-based intrusion detection do not cope with new network traffic behavior, which requires periodic computationally and time-consuming model updates. This paper proposes a novel stream learning intrusion detection model that maintains system accuracy, even in the presence of unknown traffic behavior. It also facilitates the process of updating the model, gradually incorporating new knowledge into the machine learning model. Our experiments were performed using a recent realistic dataset of network behaviors and they have shown that the proposed technique detects potentially unreliable classifications. Moreover, the proposed model can incorporate the new network traffic behavior from model updates to improve the system accuracy while maintaining its reliability. ccuracy while maintaining its reliability.
|
Author
|
Eduardo Viegas +
, Altair Santin +
, Vinicius Vielmo Cogo +
, Vilmar Abreu +
|
Booktitle
|
Proceedings of the 34th International Conference on Advanced Information Networking and Applications (AINA) +
|
Document
|
Document for Publication-Viegas2020facing.pdf +
|
Key
|
Viegas2020facing +
|
Month
|
apr +
|
NumPubDate
|
2,020.04 +
|
ResearchLine
|
Fault and Intrusion Tolerance in Open Distributed Systems (FIT) +
|
Title
|
Facing the Unknown: a Stream Learning Intrusion Detection System for Reliable Model Updates +
|
Type
|
inproceedings +
|
Year
|
2020 +
|
Has improper value forThis property is a special property in this wiki.
|
Url +
|
Categories |
Publication +
|
Modification dateThis property is a special property in this wiki.
|
28 February 2020 18:55:25 +
|