"privacy-preserving inference" Papers
2 papers found
Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization
Alexander Long, Chamin Hewa Koneputugodage, Thalaiyasingam Ajanthan et al.
NeurIPS 2025poster
Split-and-Denoise: Protect large language model inference with local differential privacy
Peihua Mai, Ran Yan, Zhe Huang et al.
ICML 2024poster