Open AccessDeep Learning Network Anomaly-Based Intrusion Detection Ensemble For Predictive Intelligence To Curb Malicious Connections: An Empirical Evidence
Author(s) -
Arnold Adimabua Ojugo,
Elohor Ekurume,
A Ojugo,
R Yoro,
A Ojugo,
A Eboka,
C Chia-Mei,
G Dah-Jyh,
H Yu-Zhi,
O Ya-Hui,
I Okobah,
A Ojugo,
A Ojugo,
A Eboka,
E Okonta,
R Yoro,
F Aghware,
H Monowar,
H Bhuyan,
H Kashyap,
D Bhattacharyya,
J Kalita,
A Ojugo,
A Eboka,
M Dadkhah,
T Sutikno,
A Ojugo,
E Ben-Iwhiwhu,
O Kekeje,
M Yerokun,
I Iyawah,
A Ojugo,
A Eboka,
A Ojugo,
A Eboka,
K Vasan,
B Surendiran,
S Tobiyama,
Y Yamaguchi,
M Rhode,
P Burnap,
K Jones,
G Loukas,
T Vuong,
M Al-Qatf,
Y Lasheng,
Y Zhang,
P Li,
X Wang,
A Ojugo,
D Otakore,
X Wang,
M Reiter,
T Ma,
F Weng,
J Cheng,
Y Yu,
X Chen,
M Mehdi,
A Zair,
M Bensebti,
A Ojugo,
A Eboka,
E Okonta,
R Yoro,
F Aghware,
K Santos,
S Chandra,
M Ratnakar,
B Dawood,
N Sudhakar,
R Thomas,
R Mark,
B Johnson,
T Croall,
J,
T Gil,
M Poletto,
M Ring,
S Wunderlich,
D Grudl,
D Landes,
A Hotho,
A Akella,
A Bharambe,
A Reiter,
M,
S Seshan,
P Munivara,
M Rama,
R Mohan,
R Venugopal,
H Nguyen,
A Angel,
S Ramamoorthy,
P Garcia-Teodoro,
J Diaz-Verdejo,
G Macia-Fernandez,
E Vazquez,
A Deepa,
D Kavitha,
R Karimazad,
A Faraahi,
R Jalili,
R Imani-Mehr,
F Amini,
M Shahriari,
Z Chen,
A Delis,
A Ojugo,
O Otakore,
A Ojugo,
A Eboka,
A Ojugo,
D Otakore,
Y Wu,
H Tseng,
W Yang,
R Jan,
K Lee,
J Kim,
K Kwon,
Y Han,
S Kim,
K Hwang,
P Dave,
S Tanachaiwiwat,
A Ojugo,
A Eboka,
R Bone,
M Crucianu,
A Ojugo,
E Ben-Iwhiwhu,
O Kekeje,
M Yerokun,
I Iyawah,
A Ojugo,
A Eboka,
K Apoorv
Publication year - 2021
Publication title -
international journal of advanced trends in computer science and engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3091
DOI - 10.30534/ijatcse/2021/851032021
Subject(s) - confusion matrix , intrusion detection system , computer science , confusion , modular design , artificial intelligence , flexibility (engineering) , sensitivity (control systems) , anomaly (physics) , network packet , machine learning , artificial neural network , intrusion , process (computing) , value (mathematics) , anomaly detection , genetic algorithm , data mining , engineering , computer security , mathematics , psychology , condensed matter physics , physics , operating system , psychoanalysis , geology , statistics , geochemistry , electronic engineering
The future is always beenshaped and refocused via Sci-Tech. Info and communication technology –has continued to shape today’s society as an inevitable driving force because we are now heavily dependent on digitally transmitted and processed data. This, is consequent upon the fact that individuals and organizations are seeking improve means to process data more effectively and efficiently. We thus, propose hybrid Genetic Algorithm trained Modular Neural Network to detect network anomaly cum malicious packets. GA was used due to its flexibility cum elitist mode. MNN is used as a learning paradigm for modular learning components. Model validation return a confusion matrix with these values: TP = 50, TN = 2, FN = 5, FP = 3. These values were subsequently applied to obtain sensitivity,specificity and accuracy of model. Model portrays a sensitivity value of 93%, specificity value of 25% and an accuracy value of 89%.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom