UQLM provides a suite of response-level scorers for quantifying the uncertainty of Large Language Model (LLM) outputs. Each scorer returns a confidence score between 0 and 1, where higher scores ...

Introduction: The Evolution of Browser Security For two decades, the web browser served as the primary security frontier for digital interactions. The logic was clear: the browser represented the lens ...

Abstract: Small uncrewed autonmous vehicles (UAVs) equipped with deep learning models are increasingly used to detect small objects both on the ground and in aerial environments. Since small objects ...

Abstract: Programming language source code vulnerability mining is crucial to improving the security of software systems, but current research is mostly focused on the C language field, with little ...