A Multi-Stage Poisoning Detection Pipeline for Embedded Voice-Command Systems
Romanian Journal of Information Science and Technology · 21.07.2026 · 29 (3) · 225-236
DOI: 10.59277/romjist.2026.3.02 ↗Kurz gefasst
Fachartikel in der Zeitschrift Romanian Journal of Information Science and Technology, online erschienen am 30.09.2026. Verfasst von Sebastian-Alexandru DRAGUSIN und 3 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben.
Abstract (Originalsprache)
Embedded voice-command systems are increasingly adopted in cyber-physical and industrial environments, yet their machine-learning pipelines remain vulnerable to data poisoning attacks that can silently degrade recognition performance or induce targeted misclassifications. This paper proposes a multi-stage poisoning detection pipeline tailored for embedded voice-command applications, combining fast integrity screening with progressively stronger detection models. First, an audio integrity layer analyzes waveform and spectrogram consistency to flag abnormal patterns indicative of injected perturbations or corrupted samples. Second, a lightweight machine-learning detector based on Random Forests operates on compact statistical descriptors extracted from spectrogram representations, enabling efficient on-device or edge-level screening. Third, a spectrogram-based Convolutional Neural Network provides high-sensitivity discrimination between clean and poisoned samples, acting as a robust validation stage in higher-assurance deployments. To increase resilience, the training procedure integrates regularization and controlled augmentation to mitigate overfitting to spurious artifacts and reduce poisoning sensitivity. The proposed approach is designed to be deployable under embedded constraints by separating low-cost screening from deeper analysis, and it offers a structured methodology for securing voice-command pipelines against poisoning threats.
Zitieren
APA
DRAGUSIN, S., TOMA, D., BOSTINARU, R., & BIZON, N. (2026). A Multi-Stage Poisoning Detection Pipeline for Embedded Voice-Command Systems. Romanian Journal of Information Science and Technology, 29(3), 225-236. https://doi.org/10.59277/romjist.2026.3.02
Vancouver
DRAGUSIN S, TOMA D, BOSTINARU R, BIZON N. A Multi-Stage Poisoning Detection Pipeline for Embedded Voice-Command Systems. Romanian Journal of Information Science and Technology. 2026;29(3):225-236. doi:10.59277/romjist.2026.3.02
BibTeX
@article{DRAGUSIN2026,
author = {DRAGUSIN, Sebastian-Alexandru and TOMA, Denisa and BOSTINARU, Robert-Nicolae and BIZON, Nicu},
title = {A Multi-Stage Poisoning Detection Pipeline for Embedded Voice-Command Systems},
journal = {Romanian Journal of Information Science and Technology},
year = {2026},
volume = {29},
number = {3},
pages = {225--236},
doi = {10.59277/romjist.2026.3.02}
}
EUVIMED