SimKey: A Semantically Aware Key Module for Watermarking Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918183269564416 |
|---|---|
| author | Kodama, Shingo Diwan, Haya Rosenblatt, Lucas Witter, R. Teal Cohen, Niv |
| author_facet | Kodama, Shingo Diwan, Haya Rosenblatt, Lucas Witter, R. Teal Cohen, Niv |
| contents | The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can embed an imperceptible signal into generated text, marking its origin. Most leading approaches seed an LLM's next-token sampling with a pseudo-random key that can later be recovered to identify the text as machine-generated, while only minimally altering the model's output distribution. However, these methods suffer from two related issues: (i) watermarks are brittle to simple surface-level edits such as paraphrasing or reordering; and (ii) adversaries can append unrelated, potentially harmful text that inherits the watermark, risking reputational damage to model owners. To address these issues, we introduce SimKey, a semantic key module that strengthens watermark robustness by tying key generation to the meaning of prior context. SimKey uses locality-sensitive hashing over semantic embeddings to ensure that paraphrased text yields the same watermark key, while unrelated or semantically shifted text produces a different one. Integrated with state-of-the-art watermarking schemes, SimKey improves watermark robustness to paraphrasing and translation while preventing harmful content from false attribution, establishing semantic-aware keying as a practical and extensible watermarking direction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12828 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SimKey: A Semantically Aware Key Module for Watermarking Language Models Kodama, Shingo Diwan, Haya Rosenblatt, Lucas Witter, R. Teal Cohen, Niv Cryptography and Security Machine Learning The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can embed an imperceptible signal into generated text, marking its origin. Most leading approaches seed an LLM's next-token sampling with a pseudo-random key that can later be recovered to identify the text as machine-generated, while only minimally altering the model's output distribution. However, these methods suffer from two related issues: (i) watermarks are brittle to simple surface-level edits such as paraphrasing or reordering; and (ii) adversaries can append unrelated, potentially harmful text that inherits the watermark, risking reputational damage to model owners. To address these issues, we introduce SimKey, a semantic key module that strengthens watermark robustness by tying key generation to the meaning of prior context. SimKey uses locality-sensitive hashing over semantic embeddings to ensure that paraphrased text yields the same watermark key, while unrelated or semantically shifted text produces a different one. Integrated with state-of-the-art watermarking schemes, SimKey improves watermark robustness to paraphrasing and translation while preventing harmful content from false attribution, establishing semantic-aware keying as a practical and extensible watermarking direction. |
| title | SimKey: A Semantically Aware Key Module for Watermarking Language Models |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2510.12828 |