Peer-reviewedCC BY 4.0Scientific Reports
SADA: semantic-aware perturbation and dual-view alignment for privacy-preserving LLMs
Related
- Federated learning with update level noise perturbation and blockchain audit logging for privacy-preserving healthcare ECG classification
- FedEAVE: federated evidence alignment and causal diagnosis for privacy-preserving personalized learning
- Equitable Partition Realizability for Dynamics-preserving and Privacy-aware Network Reconstruction
- Federated learning with adaptive reliability aware aggregation for privacy preserving healthcare IoT systems
- Privacy-Preserving Large Language Model Deployment for Oncology Registry Abstraction: Structure-Aware Evaluation in a Real-World Clinical Setting
BibTeX
@article{meng2026sada,
title = {{SADA: semantic-aware perturbation and dual-view alignment for privacy-preserving LLMs}},
author = {Bingbing Meng and Xiaoqiong Xu and Bonan Liu and Xi Chen and Ling Liu and Meng Xiao and Qiang Wang},
journal = {Scientific Reports},
year = {2026},
month = nov,
doi = {10.1038/s41598-026-76220-6},
url = {https://www.nature.com/articles/s41598-026-76220-6},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - SADA: semantic-aware perturbation and dual-view alignment for privacy-preserving LLMs
AU - Bingbing Meng
AU - Xiaoqiong Xu
AU - Bonan Liu
AU - Xi Chen
AU - Ling Liu
AU - Meng Xiao
AU - Qiang Wang
PY - 2026
DA - 2026/11/02
JO - Scientific Reports
DO - 10.1038/s41598-026-76220-6
UR - https://www.nature.com/articles/s41598-026-76220-6
SN - 2045-2322
ER -