Protecting Intellectual Property of Large Language Model-Based Code Generation APIs via Watermarks
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
The rise of large language model-based code generation (LLCG) has enabled various commercial services and APIs. Training LLCG models is often expensive and time-consuming, and the training data are often large-scale and even inaccessible to the public. As a result, the risk of intellectual property (IP) theft over the LLCG models (e.g., via imitation attacks) has been a serious concern. In this paper, we propose the first watermark (WM) technique to protect LLCG APIs from remote imitation attacks. Our proposed technique is based on replacing tokens in an LLCG output with their "synonyms" available in the programming language. A WM is thus defined as the stealthily tweaked distribution among token synonyms in LLCG outputs. We design six WM schemes (instantiated into over 30 WM passes) which rely on conceptually distinct token synonyms available in programming languages. Moreover, to check the IP of a suspicious model (decide if it is stolen from our protected LLCG API), we propose a statistical tests-based procedure that can directly check a remote, suspicious LLCG API.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., et al. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.139 · Cited by 2,824
Wang, Y., Wang, W., Joty, S., & Hoi, S. C. H. (2021) · arXiv · doi:10.48550/arxiv.2109.00859 · Cited by 1,495
Efficient transformers: A survey
Tay, Y., Dehghani, M., Bahri, D., & Metzler, D. (2023) · ACM Computing Surveys · doi:10.1145/3530811 · Cited by 1,267
Efficient Transformers: A Survey
Tay, Y., Dehghani, M., Bahri, D., & Metzler, D. (2020) · arXiv · doi:10.48550/arxiv.2009.06732 · Cited by 1,267
Unified Pre-training for Program Understanding and Generation
Ahmad, W., Chakraborty, S., Ray, B., & Chang, K.-W. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.211 · Cited by 642
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Lu, S., Guo, D., Ren, S., Huang, J., Svyatkovskiy, A., Blanco, A., Clement, C., Drain, D., Jiang, D., Tang, D., et al. (2021) · arXiv · doi:10.48550/arxiv.2102.04664 · Cited by 536
Mapping Language to Code in Programmatic Context
Iyer, S., Konstas, I., Cheung, A., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1192 · Cited by 180
(2019) · doi:10.1145/3474085.3475591 · Cited by 134
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark
He, X., Xu, Q., Lyu, L., Wu, F., & Wang, C. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21321 · Cited by 56
Self-citation
Cited by
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly
Yao, Y., Duan, J., Xu, K., Cai, Y., Sun, Z., & Zhang, Y. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100211 · Cited by 1,083
“Lee et al. [147] developed SWEET , a tool that implements watermarking specifically on tokens within programming languages.”
MethodHistory, development, and principles of large language models: an introductory survey
Wang, Z., Chu, Z., Doan, T. V., Ni, S., Yang, M., & Zhang, W. (2025) · AI and Ethics · doi:10.1007/s43681-024-00583-7 · Cited by 109
“This is essential to safeguard the legitimate rights and interests of original creators, users, and the public while fostering and respecting the innovation and advancement of LLMs technology [174].”
ModelShield: Adaptive and Robust Watermark Against Model Extraction Attack
Pang, K., Qi, T., Wu, C., Bai, M., Jiang, M., & Huang, Y. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3530691 · Cited by 29
“Similarly, the EmbMarker [41] uses a set of medium-frequency trigger words as watermark signals.”
A Systematic Comparison of Large Language Models Performance for Intrusion Detection
Bui, M.-T., Boffa, M., Valentim, R. V., Navarro, J. M., Chen, F., Bao, X., Houidi, Z. B., & Rossi, D. (2024) · Proceedings of the ACM on Networking · doi:10.1145/3696379 · Cited by 19
Li, Z., Qiu, W., Ma, P., Li, Y., Li, Y., He, S., Jiang, B., Wang, S., & Gu, W. (2024) · arXiv · doi:10.48550/arxiv.2402.01723 · Cited by 4
“Investigating the privacy risks associated with LLMs and exploring innovative privacy-enhancing methods such as watermarking [20, 42, 67], federated learning [58, 64, 66], differential privacy [48], and homomorphic encryption [25] for industrial applications is of paramount importance.”
BackgroundSelf-citation
Metadata
- Authors
- Li, Z., Wang, C., Wang, S., & Gao, C.
- Venue
- Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2023-11-15
- Pages
- 2336-2350
- OpenAlex
- W4388857114
- Cited by
- 30
- References
- 9
- FWCI
- 5.57
- Type
- conference paper
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Protecting Intellectual Property of Large Language Model-Based Code Generation APIs via Watermarks. https://app.cochat.ai/papers/10.1145/3576915.3623120
- The paper
- Li, Z., Wang, C., Wang, S., & Gao, C. (2023). Protecting Intellectual Property of Large Language Model-Based Code Generation APIs via Watermarks. Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security. https://doi.org/10.1145/3576915.3623120
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.