Zhen Wang

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 introduces PIDP-Attack, a novel compound adversarial attack that combines prompt injection with database poisoning to manipulate Retrieval-Augmented Generation (RAG) systems against arbitrary queries without prior knowledge.

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.

The paper introduces a multi-dimensional evasion framework and a new benchmark (A3S-Bench) to test autonomous agents, demonstrating that stateful, multi-turn attacks significantly increase system risk.

The paper designs and evaluates a triadic LLM-Teacher collaboration system for K-12 writing, finding that strategic labor division between the LLM and teacher effectively improves writing quality but requires dynamic adaptation as student proficiency increases.

ResMerge proposes a residual-based spectral merging framework that improves the combination of multiple reinforcement learning (RL) expert models by stabilizing the aggregation process using a residual backbone.