Practical classification accuracy of sequential data using neural networks

Many existing studies on neural network accuracy utilize datasets that may not always reflect real-world conditions. While it has been demonstrated that accuracy tends to decrease as the number of benign samples increases, this effect has not been quantitatively assessed within neural networks. More...

Full description

Saved in:
Bibliographic Details
Main Author: Mamoru Mimura
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Machine Learning with Applications
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666827024000872
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850077277666148352
author Mamoru Mimura
author_facet Mamoru Mimura
author_sort Mamoru Mimura
collection DOAJ
description Many existing studies on neural network accuracy utilize datasets that may not always reflect real-world conditions. While it has been demonstrated that accuracy tends to decrease as the number of benign samples increases, this effect has not been quantitatively assessed within neural networks. Moreover, its relevance to security tasks beyond malware classification remains unexplored. In this research, we refined the metric to evaluate the degradation of accuracy with an increased number of benign samples in test data. Utilizing both standard and specific neural network models, we conducted experiments to adapt this metric to neural networks and various feature extraction techniques. Using the FFRI dataset, comprising 150,000 malware and 400,000 benign samples, along with the URL dataset, containing 3143 malicious and 106,545,781 benign samples, we increased benign samples in the test set while keeping the training set’s malicious and benign samples constant. Our findings indicate that neural networks can indeed overestimate their accuracy with a smaller count of benign samples. Importantly, our refined metric is not only applicable to neural networks but is also effective for other feature extraction methods and security tasks beyond malware detection.
format Article
id doaj-art-8da9124bdc284224bc3a6c7667b3b092
institution DOAJ
issn 2666-8270
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Machine Learning with Applications
spelling doaj-art-8da9124bdc284224bc3a6c7667b3b0922025-08-20T02:45:50ZengElsevierMachine Learning with Applications2666-82702025-03-011910061110.1016/j.mlwa.2024.100611Practical classification accuracy of sequential data using neural networksMamoru Mimura0National Defense Academy, 1-10-20 Hashirimizu, Yokosuka, Kanagawa, JapanMany existing studies on neural network accuracy utilize datasets that may not always reflect real-world conditions. While it has been demonstrated that accuracy tends to decrease as the number of benign samples increases, this effect has not been quantitatively assessed within neural networks. Moreover, its relevance to security tasks beyond malware classification remains unexplored. In this research, we refined the metric to evaluate the degradation of accuracy with an increased number of benign samples in test data. Utilizing both standard and specific neural network models, we conducted experiments to adapt this metric to neural networks and various feature extraction techniques. Using the FFRI dataset, comprising 150,000 malware and 400,000 benign samples, along with the URL dataset, containing 3143 malicious and 106,545,781 benign samples, we increased benign samples in the test set while keeping the training set’s malicious and benign samples constant. Our findings indicate that neural networks can indeed overestimate their accuracy with a smaller count of benign samples. Importantly, our refined metric is not only applicable to neural networks but is also effective for other feature extraction methods and security tasks beyond malware detection.http://www.sciencedirect.com/science/article/pii/S2666827024000872Machine learningBinary classificationBenign sampleDeep neural networkRecurrent neural networkLong short-term memory
spellingShingle Mamoru Mimura
Practical classification accuracy of sequential data using neural networks
Machine Learning with Applications
Machine learning
Binary classification
Benign sample
Deep neural network
Recurrent neural network
Long short-term memory
title Practical classification accuracy of sequential data using neural networks
title_full Practical classification accuracy of sequential data using neural networks
title_fullStr Practical classification accuracy of sequential data using neural networks
title_full_unstemmed Practical classification accuracy of sequential data using neural networks
title_short Practical classification accuracy of sequential data using neural networks
title_sort practical classification accuracy of sequential data using neural networks
topic Machine learning
Binary classification
Benign sample
Deep neural network
Recurrent neural network
Long short-term memory
url http://www.sciencedirect.com/science/article/pii/S2666827024000872
work_keys_str_mv AT mamorumimura practicalclassificationaccuracyofsequentialdatausingneuralnetworks