Reducing Instability in Synthetic Data Evaluation with a Super-Metric in MalDataGen

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: da Silva, Anna Luiza Gomes, Kreutz, Diego, Diniz, Angelo, Mansilha, Rodrigo, da Fonseca, Celso Nobre
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917095992721408
author da Silva, Anna Luiza Gomes
Kreutz, Diego
Diniz, Angelo
Mansilha, Rodrigo
da Fonseca, Celso Nobre
author_facet da Silva, Anna Luiza Gomes
Kreutz, Diego
Diniz, Angelo
Mansilha, Rodrigo
da Fonseca, Celso Nobre
contents Evaluating the quality of synthetic data remains a persistent challenge in the Android malware domain due to instability and the lack of standardization among existing metrics. This work integrates into MalDataGen a Super-Metric that aggregates eight metrics across four fidelity dimensions, producing a single weighted score. Experiments involving ten generative models and five balanced datasets demonstrate that the Super-Metric is more stable and consistent than traditional metrics, exhibiting stronger correlations with the actual performance of classifiers.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16373
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reducing Instability in Synthetic Data Evaluation with a Super-Metric in MalDataGen
da Silva, Anna Luiza Gomes
Kreutz, Diego
Diniz, Angelo
Mansilha, Rodrigo
da Fonseca, Celso Nobre
Artificial Intelligence
Machine Learning
68T01
I.2
Evaluating the quality of synthetic data remains a persistent challenge in the Android malware domain due to instability and the lack of standardization among existing metrics. This work integrates into MalDataGen a Super-Metric that aggregates eight metrics across four fidelity dimensions, producing a single weighted score. Experiments involving ten generative models and five balanced datasets demonstrate that the Super-Metric is more stable and consistent than traditional metrics, exhibiting stronger correlations with the actual performance of classifiers.
title Reducing Instability in Synthetic Data Evaluation with a Super-Metric in MalDataGen
topic Artificial Intelligence
Machine Learning
68T01
I.2
url https://arxiv.org/abs/2511.16373