3 papers
cs.CR2026
Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM
Jisung Park, John Le, Heath Cooper
GraphRAG pipelines construct auxiliary structures during offline indexing--semantic summaries, hierarchical edges, and pre-computed scores--that determine how retrieval is prioriti…
cs.CR2026
TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems
Ngoc Bao Anh Le, Thai T. Vu, John Le +2
Existing homomorphic encryption (HE)-based GNN systems adopt a graph-centric paradigm that couples per-query cost to global graph size, limiting evaluations to at most ~20k nodes a…
cs.CL2025
RAID: Refusal-Aware and Integrated Decoding for Jailbreaking LLMs
Tuan T. Nguyen, John Le, Thai T. Vu +2
Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. We present RAID (Refusal-…