Tag: differential privacy
Synthetic Data Generation to Protect Privacy in LLM Training
Learn how synthetic data generation with differential privacy protects user data during LLM training. Discover techniques like DP-SGD and LoRA that balance privacy guarantees with model utility.
Data Privacy for Large Language Models: Principles and Practical Controls
LLMs memorize personal data from training sets, risking leaks and regulatory fines. Learn the seven core privacy principles and four practical controls - like differential privacy and LLM-based PII detection - that actually work.
