一作ACL 2026Poster· Natural Language Processing
C ode R ipple: Wavelet-Based Detection of LLM -Generated Code
Xingyu Yao · Zhendong Mao · Quan Wang
摘要
Detecting LLM-generated code is crucial for ensuring software provenance, security, reliability, and licensing compliance. Existing training-free detectors, mostly adapted from text-based methods, rely on global statistics of the Token Perplexity Sequence (TPS) and struggle with code. We reveal a...