Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
The Real-Time IoT Data Security. / Hakizimana, E; Dik, G; Gervasi, O (редактор); Murgante, B (редактор); Garau, C (редактор); Karaca, Y (редактор); Lago, MNF (редактор); Scorza, F (редактор); Braga, AC (редактор).
COMPUTATIONAL SCIENCE AND ITS APPLICATIONS-ICCSA 2025 WORKSHOPS, PT XIII. Springer Nature, 2026. стр. 364-374 (Lecture Notes in Computer Science; Том 15898 LNCS).Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
}
TY - GEN
T1 - The Real-Time IoT Data Security
AU - Hakizimana, E
AU - Dik, G
A2 - Gervasi, O
A2 - Murgante, B
A2 - Garau, C
A2 - Karaca, Y
A2 - Lago, MNF
A2 - Scorza, F
A2 - Braga, AC
N1 - Times Cited in Web of Science Core Collection: 0 Total Times Cited: 0 Cited Reference Count: 13
PY - 2026
Y1 - 2026
N2 - Our main area of study is IoT security, including its effects and ways to mitigate them in real time. This study focuses on Distributed Denial-of-Service (DDoS) assaults, which pose a serious risk to Internet of Things networks because of the growing number of unprotected devices. We examine the characteristics of DDoS attacks, examine the strategies to detect it, especially in the African setting, and suggest a detection methodology based on algorithms from Adaptive Resonance Theory (ART) and Long Short-Term Memory (LSTM). The detection performance is evaluated using metrics such as F1-score, precision, and recall. By offering an efficient DDoS detection framework, the study helps to improve real-time IoT data security.
AB - Our main area of study is IoT security, including its effects and ways to mitigate them in real time. This study focuses on Distributed Denial-of-Service (DDoS) assaults, which pose a serious risk to Internet of Things networks because of the growing number of unprotected devices. We examine the characteristics of DDoS attacks, examine the strategies to detect it, especially in the African setting, and suggest a detection methodology based on algorithms from Adaptive Resonance Theory (ART) and Long Short-Term Memory (LSTM). The detection performance is evaluated using metrics such as F1-score, precision, and recall. By offering an efficient DDoS detection framework, the study helps to improve real-time IoT data security.
KW - Distributed Denial-of-Service (DDoS)
KW - Real-time Detection
KW - Long Short-Term Memory (LSTM)
KW - Adaptive Resonance Theory (ART)
KW - Machine Learning
KW - Cybersecurity
KW - Network Security
KW - Africa
UR - https://www.mendeley.com/catalogue/a23c141d-9598-3e6e-8826-d5473ddf4daf/
U2 - 10.1007/978-3-031-97657-5_22
DO - 10.1007/978-3-031-97657-5_22
M3 - статья в сборнике материалов конференции
SN - 978-3-031-97656-8
SN - 978-3-031-97657-5
T3 - Lecture Notes in Computer Science
SP - 364
EP - 374
BT - COMPUTATIONAL SCIENCE AND ITS APPLICATIONS-ICCSA 2025 WORKSHOPS, PT XIII
PB - Springer Nature
Y2 - 30 June 2025 through 3 July 2025
ER -
ID: 151949096