Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Boyu, He, Ping, Du, Tianyu, Zhang, Xuhong, Yun, Lei, Chow, Kingsum, Yin, Jianwei
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.13982
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916954758971392
author Zhang, Boyu
He, Ping
Du, Tianyu
Zhang, Xuhong
Yun, Lei
Chow, Kingsum
Yin, Jianwei
author_facet Zhang, Boyu
He, Ping
Du, Tianyu
Zhang, Xuhong
Yun, Lei
Chow, Kingsum
Yin, Jianwei
contents With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current watermarking techniques have the potential to identify the code LM to protect its IP, they have limitations when facing the more practical and complex demand, i.e., offering the individual user-level tracing in the black-box setting. This work presents CLMTracing, a black-box code LM watermarking framework employing the rule-based watermarks and utility-preserving injection method for user-level model tracing. CLMTracing further incorporates a parameter selection algorithm sensitive to the robust watermark and adversarial training to enhance the robustness against watermark removal attacks. Comprehensive evaluations demonstrate CLMTracing is effective across multiple state-of-the-art (SOTA) code LMs, showing significant harmless improvements compared to existing SOTA baselines and strong robustness against various removal attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13982
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
Zhang, Boyu
He, Ping
Du, Tianyu
Zhang, Xuhong
Yun, Lei
Chow, Kingsum
Yin, Jianwei
Programming Languages
With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current watermarking techniques have the potential to identify the code LM to protect its IP, they have limitations when facing the more practical and complex demand, i.e., offering the individual user-level tracing in the black-box setting. This work presents CLMTracing, a black-box code LM watermarking framework employing the rule-based watermarks and utility-preserving injection method for user-level model tracing. CLMTracing further incorporates a parameter selection algorithm sensitive to the robust watermark and adversarial training to enhance the robustness against watermark removal attacks. Comprehensive evaluations demonstrate CLMTracing is effective across multiple state-of-the-art (SOTA) code LMs, showing significant harmless improvements compared to existing SOTA baselines and strong robustness against various removal attacks.
title CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
topic Programming Languages
url https://arxiv.org/abs/2509.13982