2 papers
cs.CR2026
Your Model Is Leaking: Covert Information Transfer through LLM Residual Streams
Mingyuan Li, Yanna Jiang, Guangsheng Yu +4
Privacy-sensitive organizations may run large language models (LLMs) in restricted or air-gapped environments while exporting selected diagnostic artifacts. We show that a compromi…
cs.CR2026
MDRC: A Deployable State-Recovery Defense for Traffic Signal Control under Sensor Corruption
Mingyuan Li, Chunyu Liu, Xiao Liu +5
Traffic Signal Control (TSC) is a safety-critical cyber-physical system that relies on real-time sensing. Corrupted observations caused by adversarial perturbations or sensor failu…