Securing LLM-in-the-loop software for empirical study of risks, mitigations, and utility trade-offs in a safety-critical case

作者：Wei Wang, Jing Liu, Bruce Gu, Changwei Wang, Y.Neil Qu, Dongqin Feng · 发表于：Empirical Software Engineering · 年份：2026 · DOI：10.1007/s10664-026-10820-8 · 研究领域：Adversarial Robustness in Machine Learning、Security and Verification in Computing、Blockchain Technology Applications and Security