1 citations
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation
Rana Muhammad Ahmed, Sabahat Abbas
Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution rows to 180 model-bound reques…
cs.CR2026★ 1 cited
DAIRE: A lightweight AI model for real-time detection of Controller Area Network attacks in the Internet of Vehicles
Shahid Alam, Amina Jameel, Zahida Parveen +4
The Internet of Vehicles (IoV) is advancing modern transportation by improving safety, efficiency, and intelligence. However, the reliance on the Controller Area Network (CAN) intr…