Design of an IoT DDoS attack prediction system based on data mining technology

Due to the rise of the Internet of things (IoT), the threat to information security extends from general servers to IoT devices. Possible IoT security issues include all kinds of network attacks. Distributed denial-of-service (DDoS) attacks are notoriously difficult to prevent. With the continuous e...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:The Journal of supercomputing Ročník 78; číslo 4; s. 4601 - 4623
Hlavný autor: Huang, Lingfeng
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.03.2022
Springer Nature B.V
Predmet:
Algorithms
Classification
Compilers
Computer Science
Cybersecurity
Data mining
Data Mining for IoT in Mobile Edge computing
Denial of service attacks
Internet of Things
Interpreters
Modules
Packets (communication)
Prediction models
Processor Architectures
Programming Languages
Support vector machines
Systems design
Data mining
Cyberattack
Internet of things (IoT)
Distributed denial-of-service (DDoS)
ISSN:0920-8542, 1573-0484
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Due to the rise of the Internet of things (IoT), the threat to information security extends from general servers to IoT devices. Possible IoT security issues include all kinds of network attacks. Distributed denial-of-service (DDoS) attacks are notoriously difficult to prevent. With the continuous evolution of DDoS attacks, from simple network packet attacks, it has become possible for hackers to hide in legitimate paths. At times, large numbers of non-legitimate attack packets can occur, which can be a major problem that enterprises cannot protect themselves against. This paper proposes a data-mining technology-based DDoS attack prediction system, designed for use in the IoT environment. The system can be divided into two major modules: 1. the DDoS attack prediction model-construction module and 2. the DDoS attack prediction defence module. In the DDoS attack prediction model-construction module, through the integration of data-mining classification technology, the SVM algorithm is used to dig out the classification basis of a possible attack. The attack prediction model is then established, and the prediction result is corrected in real time. The results of the study conducted showed that when an attacker attempts to launch an attack, the system design will predict the timing of the DDoS attack, and existing IP backtracking technology can be used to track the source of the attack, block the source of the attack in advance and achieve the purpose of defence.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-021-04055-1