An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic 文章

ArXiv CS.CL2026-06-05NEWSen作者: Shuze Liu, Qianwen Guo, Yushun Dong
查看原文 →
关系图谱

An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic · 相关技术

相关技术

CAPmarginal MahalanobisATESeataPRADAlocal maximum mean discrepancylarge language models