Improving data-driven inferential sensor modeling by industrial knowledge: A bayesian perspective

Z Chen, H Wang, Z Song, Z Ge - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Accurate quality variable inference by process variables is the core of industrial inferential
sensor modeling, where recent advancements have seen deep learning (DL) models …

Preventing Non-intrusive Load Monitoring Privacy Invasion: A Precise Adversarial Attack Scheme for Networked Smart Meters

J He, J Wang, N Wang, S Guo, L Zhu, D Niyato… - arxiv preprint arxiv …, 2024 - arxiv.org
Smart grid, through networked smart meters employing the non-intrusive load monitoring
(NILM) technique, can considerably discern the usage patterns of residential appliances …

Maintaining Privacy in Smart Grid: Utilizing the Adversarial Attack Paradigm to Counter Non-Intrusive Load Monitoring Models

J He, T **ang, T Wu, Z Chen, N Wang… - IEEE Internet of Things …, 2024 - ieeexplore.ieee.org
The non-intrusive load monitoring (NILM) technique, through its use of various deep neural
networks (DNNs), is capable of learning residential appliances' usage patterns from …

[HTML][HTML] Soft-Label Supervised Meta-Model with Adversarial Samples for Uncertainty Quantification

K Lucke, A Vakanski, M **an - Computers, 2025 - mdpi.com
Despite the recent success of deep-learning models, traditional models are overconfident
and poorly calibrated. This poses a serious problem when applied to high-stakes …

[PDF][PDF] ИССЛЕДОВАНИЕ СОСТЯЗАТЕЛЬНЫХ АТАК НА РЕГРЕССИОННЫЕ МОДЕЛИ МАШИННОГО ОБУЧЕНИЯ В БЕСПРОВОДНЫХ СЕТЯХ 5G

ЛВ Легашев, АЮ Жигалов - Вопросы кибербезопасности, 2024 - cyberrus.info
Метод исследования: Эмуляция данных распространения сигнала в MIMO системах,
синтез состязательных примеров, выполнение состязательных атак на модели …