Xiaoying Zhang

Local Differential Privacy with K-anonymous for Frequency Estimation

2019

Data release, such as statistics of data distribution, in many data analysis and machine learning tasks is needed, which poses significant risks of user's privacy. Usually, to preserve privacy of every individual, frequency estimation based …

Human-Instruction-Free LLM Self-Alignment with Limited Samples

2024 · arXiv (Cornell University)

Aligning large language models (LLMs) with human values is a vital task for LLM practitioners. Current alignment techniques have several limitations: (1) requiring a large amount of annotated data; (2) demanding heavy human involvement; (3) …