2015
DOI: 10.1080/09540091.2015.1031082
|View full text |Cite
|
Sign up to set email alerts
|

Distributed reinforcement learning for adaptive and robust network intrusion response

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
22
0

Year Published

2017
2017
2023
2023

Publication Types

Select...
6
2
1
1

Relationship

1
9

Authors

Journals

citations
Cited by 34 publications
(22 citation statements)
references
References 8 publications
0
22
0
Order By: Relevance
“…Specify a key folder to hold the normal data as comparison model. 3 We use 7 ways to simulate attacks the computers, and save the attack packets to the key folder, through which we can better evaluate the established network intrusion detection system. According to the error rate of the search engine for anomaly detection, we can intuitively evaluate the established intrusion detection system.…”
Section: Test Methodsmentioning
confidence: 99%
“…Specify a key folder to hold the normal data as comparison model. 3 We use 7 ways to simulate attacks the computers, and save the attack packets to the key folder, through which we can better evaluate the established network intrusion detection system. According to the error rate of the search engine for anomaly detection, we can intuitively evaluate the established intrusion detection system.…”
Section: Test Methodsmentioning
confidence: 99%
“…Malialis et al [16] propose Multiagent Router Throttling. This approach aims to defend the system against DDoS attacks and consists of a set of RL agents installed on multiple routers.…”
Section: (Distribute) Denial Of Service Attack ((D)dos)mentioning
confidence: 99%
“…The proposed approach is more secure, autonomous, scalable and it achieves better performance when compared to other related approaches. In [326], the authors have proposed a new distributed scalable framework for ID and response system based on RL. The proposed decentralized approach is designed especially for DDoS detection and response.…”
Section: A Reinforcement Learning Based Intrusion Detectionmentioning
confidence: 99%