3 papers
cs.CR2026
Poisoning the Neighborhood: A Topology-Aware Topic-Level Attack on Large-Scale HNSW-based RAG Systems
Yufei Chen, Yao Wang, Haibin Zhang
Retrieval-augmented generation (RAG) mitigates hallucinations and knowledge staleness in large language models using external knowledge. However, ingestion from public and third-pa…
cs.AI2026
Beyond Suspicious Steps: Ontological Trust in Long-Horizon Agents
An He, Yao Wang, Haibin Zhang
Long-horizon agents increasingly operate across many steps, tools, and observa- tions. In this setting, the relevant oversight question is not only whether each action is locally v…
cs.CR2025
Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems via Knowledge Asymmetry Exploitation
Yufei Chen, Yao Wang, Haibin Zhang +1
Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge bases, but this advancement introduces significant privacy risks…