Detection of false data injection in point-of-sale systems during credit card transactions using tuned deep learning models and oversampling techniques

Guardat en:
Dades bibliogràfiques
Publicat a:PeerJ Computer Science (Nov 7, 2025)
Autor principal: Ida, S Jhansi
Altres autors: Balasubadra, K
Publicat:
PeerJ, Inc.
Matèries:
Accés en línia:Citation/Abstract
Full Text + Graphics
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3269734329
003 UK-CbPIL
022 |a 2376-5992 
024 7 |a 10.7717/peerj-cs.3279  |2 doi 
035 |a 3269734329 
045 0 |b d20251107 
100 1 |a Ida, S Jhansi 
245 1 |a Detection of false data injection in point-of-sale systems during credit card transactions using tuned deep learning models and oversampling techniques 
260 |b PeerJ, Inc.  |c Nov 7, 2025 
513 |a Journal Article 
520 3 |a BackgroundFalse data injection attack (FDIA) occurs during credit card transactions at point-of-sale systems (POS). FDI increases in POS due to free WIFI access at sales counters. FDIA occurs through novel hardware attacks such as side channel, readout-bypass, and control flow attacks. The false data injection in POS leads to a data breach and financial loss to the customer and the seller/credit card owner.MethodTo solve the above problem, we have developed architecture-tuned deep learning models such as random search (RS), artificial neural network (ANN), Bayesian optimized (BO), convolutional neural network (CNN), long short term memory (LSTM), Hyperband (HB), Autoencoder (AE). Moreover, tuned architecture model access is increased through oversampling methods such as random oversampling (ROS), synthetic minority oversampling (SMOTE), adaptive synthetic sampling (ADASYN), synthetic minority oversampling for nominal and continuous features (SMOTENC), and Borderline SMOTE (BL-SMOTE). BO-CNNLSTM model with SMOTE detects FDIA attack quickly and correctly to reduce overfitting of data through optimizing the number of hidden units of the LSTM model.ResultsHence, the proposed BO-CNNLSTM model achieves an accuracy of about 98%, a precision of about 94%, a recall of about 96%, and an F1-score of about 96%. 
653 |a Machine learning 
653 |a Software 
653 |a Personal information 
653 |a Data integrity 
653 |a Oversampling 
653 |a Deep learning 
653 |a Computer architecture 
653 |a Adaptive sampling 
653 |a Artificial neural networks 
653 |a Credit card fraud 
653 |a Fraud prevention 
653 |a Malware 
653 |a Cybercrime 
653 |a Merchant banks 
653 |a Denial of service attacks 
653 |a Credit card processing 
653 |a Point of sale systems 
653 |a Servers 
653 |a Data transmission 
700 1 |a Balasubadra, K 
773 0 |t PeerJ Computer Science  |g (Nov 7, 2025) 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3269734329/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3269734329/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch