Author

Shu-Ze Liu

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Jun 2026

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

This work forms model extraction monitoring as benign-calibrated traffic-window distribution testing: embed incoming queries into a semantic space and test whether their aggregate distribution deviates from historical benign traffic.

Shu-Ze Liu, Qian-Wen Guo, Yushun Dong · arXiv.org · 1 citation