2021 International Conference on Computer Communication and Informatics (ICCCI) 2021
DOI: 10.1109/iccci50826.2021.9402441
|View full text |Cite
|
Sign up to set email alerts
|

DDOS Attack Identification using Machine Learning Techniques

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
3
2

Relationship

0
8

Authors

Journals

citations
Cited by 20 publications
(4 citation statements)
references
References 9 publications
0
4
0
Order By: Relevance
“…The most effective methods for using alreadygathered data are those that use machine learning. With more data available, categorization accuracy improves [52] However, problems including a lack of datasets, hostile assaults, and model robustness continue to exist. Further investigation is required due to the requirement for interpretable ML models for security experts and regulatory compliance.…”
Section: Discussionmentioning
confidence: 99%
“…The most effective methods for using alreadygathered data are those that use machine learning. With more data available, categorization accuracy improves [52] However, problems including a lack of datasets, hostile assaults, and model robustness continue to exist. Further investigation is required due to the requirement for interpretable ML models for security experts and regulatory compliance.…”
Section: Discussionmentioning
confidence: 99%
“…The classification of its speed as bits or bytes is discussed above in Table 1. It is [62] REVIEW 4 of 25 are 40 Gigabit Ethernet, 100 Gigabit Ethernet, and InfiniBand [22]. A Cisco Report predicted that the internet protocol may cross 4.3 zettabytes in 2023, which is 1879 exabytes higher than 2018 [3].…”
Section: Architecture Of High-speed Networkmentioning
confidence: 99%
“…Machine-Learning-Based Smart Detection System 6.9.1. General Information This smart detection system [88] works on the identification of DDOS attacks using Machine-Learning techniques such as XGBoost (Section 4.11.2), AdaBoost, Random Forests (Section 4.11.1), and multilayer perceptron. They focused on fewer features and used less memory to reduce complexity and improve the system's efficiency.…”
Section: Workingmentioning
confidence: 99%
“…The authors [88] built their classification model using XGBoost (Section 4.11.2), Ad-aBoost, Random Forests (Section 4.11.1), and multilayer perceptron, which uses the CI-CIDS2017 dataset for training. After training, their system can classify the test data into either DDoS attacks or benign ones.…”
Section: Ddos Detection Using a Machine-learning-based Smart Detectio...mentioning
confidence: 99%