3 papers
cs.CR2026
NetInspector: Measuring and Improving LLM Capabilities for Reliable Intent-Based Networking Policy Generation
Yuxuan Zhang, Hongxin Hu, Guofei Gu
Modern networks are large in scale and heterogeneous in configuration, making manual policy management increasingly impractical. Intent-Based Networking (IBN) addresses this by aut…
cs.CR2026
Origin Is All You Need: Provenance-Aware Transformers for Structural Trust-Boundary Separation
Yuxuan Zhang, Jeff Huang, Guofei Gu
Indirect prompt injection (IPI) remains a central safety and security challenge for large language model (LLM) systems because standard transformers lack architectural notion of so…
cs.CR2026
TraceScope: Interactive URL Triage via Decoupled Checklist Adjudication
Haolin Zhang, William Reber, Yuxuan Zhang +2
Modern phishing campaigns increasingly evade snapshot-based URL classifiers using interaction gates (e.g., checkbox/slider challenges), delayed content rendering, and logo-less cre…