Azala

Feasibility of Conditional Variational Autoencoders for Phase-Averaged Synthetic Time Series

Gorde:
Argitaratua izan da:European Conference on Cyber Warfare and Security (Jun 2025), p. 614-622
Egile nagusia: Rüb, Matthias
Beste egile batzuk: Grüber, Jens, Schotten, Hans
Argitaratua:
Academic Conferences International Limited
Gaiak:
Cybersecurity
Gait
Methods
Datasets
Anomalies
Artificial intelligence
Time series
Biometrics
Synthetic data
Case studies
Classification
Training
Health services
Property
Telecommunications
Data quality
Health care
Feasibility
Data
Sarrera elektronikoa:Citation/Abstract
Full Text
Full Text - PDF
Etiketak: Etiketa erantsi
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
Laburpena:In cybersecurity, synthetic data is beneficial for testing, training, and enhancing Al-driven defense systems without compromising sensitive information. Critical sectors like telecommunications, finance, energy, and healthcare generate vast amounts of time-series data, often requiring reduction methods such as phase-averaging to manage scale. However, this can obscure essential features, impacting anomaly detection and threat modeling. This study explores whether conditional Variational Autoencoders (cVAEs) can generate high-quality synthetic data when given only phase-averaged time series for training. Results on a biometric use-case show that cVAEs preserve intrinsic properties of reduced data, making it usable for classification and to a more restricted degree as training data in downstream cybersecurity applications.
Baliabidea:Political Science Database