3 papers
cs.SE2026
Beyond the Editing Canvas: Evidence Divergence in OOXML-to-LLM Ingestion
Side Liu, Jiangpeng Liu, Jinwen Xin +2
LLM pipelines increasingly ingest Office Open XML (OOXML) documents (Word, Excel, and PowerPoint files) as first-class evidence in financial, compliance, and retrieval-augmented wo…
cs.CR2026
Semantic Integrity Failures in Document-to-LLM Supply Chains
Side Liu, Jiang Ming
Document-to-LLM applications typically read uploaded PDFs by first translating them into text through a hidden extraction layer that users cannot observe or audit. We show that thi…
cs.CR2025
Analyzing PDFs like Binaries: Adversarially Robust PDF Malware Analysis via Intermediate Representation and Language Model
Side Liu, Jiang Ming, Guodong Zhou +3
Malicious PDF files have emerged as a persistent threat and become a popular attack vector in web-based attacks. While machine learning-based PDF malware classifiers have shown pro…