2 papers
cs.CL2025
Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?
Yujin Choi, Youngjoo Park, Junyoung Byun +2
Retrieval-augmented generation (RAG) mitigates the hallucination problem in large language models (LLMs) and has proven effective for personalized usages. However, delivering priva…
cs.LG2024
Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training
Yujin Choi, Jinseong Park, Junyoung Byun +1
Programmatically generated synthetic data has been used in differential private training for classification to enhance performance without privacy leakage. However, as the syntheti…