An adaptive distribution-matched recurrent network for wind power prediction using time-series distribution period division

A Meng, H Zhang, Z Dai, Z Xian, L Xiao, J Rong, C Li… - Energy, 2024 - Elsevier
Precise wind power prediction (WPP) can address the issue caused by large-scale wind
power grid integration to the power system operation. Most WPP research focus on the …

Correcting the distribution of batch normalization signals for Trojan mitigation

X Li, Z Xiang, DJ Miller, G Kesidis - Neurocomputing, 2025 - Elsevier
Backdoor (Trojan) attacks represent a significant adversarial threat to deep neural networks
(DNNs). In such attacks, the presence of an attacker's backdoor trigger causes a test …

Cooperative performance assessment for multiagent systems based on the belief rule base with continuous inputs

H Zhang, R Yang, W He, Z Feng - Information Sciences, 2024 - Elsevier
By dint of the advantage of deeply integrating empirical knowledge and monitoring data, the
belief rule base (BRB) is widely used to assess the performance of complex systems …

Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser

A Verma, AV Subramanyam, S Bangar, N Lal… - arXiv preprint arXiv …, 2023 - arxiv.org
Certified defense methods against adversarial perturbations have been recently
investigated in the black-box setting with a zeroth-order (ZO) perspective. However, these …

Transferable Adversarial Attack Based on Sensitive Perturbation Analysis in Frequency Domain

Y Liu, C Li, Z Wang, H Wu, X Zhang - Information Sciences, 2024 - Elsevier
Recently, transferable adversarial attacks on deep neural networks (DNNs) have attracted
significant attention. Although existing adversarial attacks have achieved high attack …

Generative and adversarial learning for object recognition

A Verma, AV Subramanyam, RR Shah - 2023 - repository.iiitd.edu.in
Generative modeling and adversarial learning have significantly advanced the field of
computer vision, particularly in object recognition and synthesis, unsupervised domain …