K-TCDP: A Temporal Correlated DP Mechanism for LoRA Supervised Fine-Tuning

This research proposes K-TCDP (K-Temporal Correlated Differential Privacy), a new method for training large language models privately using LoRA (a technique that adds small trainable adapters to a model). Standard privacy-preserving training adds random noise that degrades model quality, but K-TCDP uses strategically correlated noise over time so that noise added in early steps can be partially canceled out by noise in later steps, improving model performance while maintaining privacy guarantees.