Edge-HetIoT Defense against DDoS attack using LearningTechniques

Mahadik, Shalaka S.; Pawar, Pranav M.; Muthalagu, Raja

doi:10.21203/rs.3.rs-2164979/v1

Cited by 2 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this thesis acknowledges the ongoing difficulty in detecting DDoS attacks, which continue to pose a significant threat to networks. Despite the extensive efforts made by researchers, DDoS threats and (Mahadik et al, 2022) "Edge-HetIoT Defense against DDoS attacks using Learning techniques" CNN-LSTM 92.00 (Kumar et al, 2023) "DDoS Detection using Deep Learning" LSTM 98.00 (Badamasi et al, 2020)…”

Section: Discussionmentioning

confidence: 99%

Effective Intrusion Detection System Using Deep Learning for DDoS Attacks

Shaikh,

Butt,

Naqvi

2024

ABBDM

View full text Add to dashboard Cite

An increasing demand for information technology and cloud computing has led to various security threats over internet. Amongst all types of threats, Distributed Denial of Service (DDoS) attacks are the most common, posing a challenge to a cyber security. It allows unauthorized users to gain access to services, and preventing authorized users. Traditional intrusion detection, antivirus software, and firewalls are not enough to detect these attacks. This paper proposed an efficient deep learning-based intrusion detection system (IDS) for DDoS attacks detection. Proposed model is a hybrid CNN-LSTM model which is combination of best DL algorithms to take advantage of CNN to extract spatial features and LSTM to extract temporal features. The real-time DDoS-specific benchmark-dataset CICDDoS2019 used for training, testing, and validation. An autoencoder has been used for dimensionality reduction, and SMOTE method is used to balance the minority class of dataset. The experimental results proved that the model outperforms than other state-of-the-art models, with an accuracy score of 99.86%.

show abstract

Section: Discussionmentioning

confidence: 99%

Effective Intrusion Detection System Using Deep Learning for DDoS Attacks

Shaikh,

Butt,

Naqvi

2024

ABBDM

View full text Add to dashboard Cite

show abstract

A DNN Architecture Generation Method for DDoS Detection via Genetic Alogrithm

Zhao

Chen

et al. 2023

Future Internet

View full text Add to dashboard Cite

Nowdays, DNNs (Deep Neural Networks) are widely used in the field of DDoS attack detection. However, designing a good DNN architecture relies on the designer’s experience and requires considerable work. In this paper, a GA (genetic algorithm) is used to automatically generate the DNN architecture for DDoS detection to minimize human intervention in the design process. Furthermore, given the complexity of contemporary networks and the diversity of DDoS attacks, the objective of this paper is to generate a DNN model that boasts superior performance, real-time capability, and generalization ability to tackle intricate network scenarios. This paper presents a fitness function that guarantees the best model generated possesses a specific level of real-time capability. Additionally, the proposed method employs multiple datasets to joint models generated, thereby enhancing the model’s generalization performance. This paper conducts several experiments to validate the viability of the proposed method. Firstly, the best model generated with one dataset is compared with existing DNN models on the CICDDoS2019 dataset. The experimental results indicate that the model generated with one dataset has higher precision and F1-score than the existing DNN models. Secondly, model generation experiments are conducted on the CICIDS2017 and CICIDS2018 datasets, and the best model generated still performs well. Finally, this paper conducts comparative experiments on multiple datasets using the best model generated with six datasets and the best model generated by existing methods. The experimental results demonstrate that the best model generated with six datasets has better generalization ability and real-time capability.

show abstract

Edge-HetIoT Defense against DDoS attack using LearningTechniques

Cited by 2 publications

References 27 publications

Effective Intrusion Detection System Using Deep Learning for DDoS Attacks

Effective Intrusion Detection System Using Deep Learning for DDoS Attacks

A DNN Architecture Generation Method for DDoS Detection via Genetic Alogrithm

Contact Info

Product

Resources

About