Yizhen Wang
3 indexed papers
Research Timeline
The paper introduces CodeScan, a novel black-box framework that detects data poisoning in code generation LLMs by analyzing structural similarities across multiple generations to identify recurring, vulnerable code structures.
The paper proposes an optimized, end-to-end privacy-preserving framework for vertical federated learning by distributing aggregation roles across multiple servers using secure multiparty computation and differential privacy.
This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preservation.
Papers
A Survey on Split Learning for LLM Fine-Tuning: Models, Systems, and Privacy Optimizations
Zihan Liu, Yizhen Wang, Rui Wang, Xiu Tang +1 more
This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preserv…