Dataset Watermarking for Closed LLMs with Provable Detection

• URL: http://arxiv.org/abs/2605.06865v1
• Date: Thu, 07 May 2026 19:06:35 GMT
• Title: Dataset Watermarking for Closed LLMs with Provable Detection
• Abstract summary: Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data.<n>This motivates the need for dataset watermarking: designing datasets such that training on them leaves detectable signatures in the resulting model.<n>We introduce the first dataset watermarking method for closed LLMs with provable detection.
• Score: 45.743499931376704
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may have been trained on proprietary datasets or the same benchmarks used for evaluation. This motivates the need for dataset watermarking: designing datasets such that training on them leaves detectable signatures in the resulting model. Prior work has explored this problem for open models. We introduce the first dataset watermarking method for closed LLMs with provable detection. In particular, we embed a dataset-level watermark signal by increasing the co-occurrence frequency of randomly selected word pairs through rephrasing, and detect it using a statistical test on co-occurrence patterns in model-generated outputs. We evaluate our method with multiple base models and benchmark datasets and show that it reliably detects the watermark ($p <0.01$) in the fine-tuning stage. Notably, our method remains effective in a data mixture setting where the watermarked dataset constitutes only approximately $1\%$ of the total fine-tuning tokens. Furthermore, we show that our method preserves the utility and semantic integrity of the benchmark.

Related papers

• CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking [85.68235482145091]
  Large-scale speech datasets have become valuable intellectual property.<n>We propose a novel dataset ownership verification method.<n>Our approach introduces a clustering-based backdoor watermark (CBW)<n>We conduct extensive experiments on benchmark datasets, verifying the effectiveness and robustness of our method against potential adaptive attacks.
  arXiv  Detail & Related papers  (2025-03-02T02:02:57Z)
• Ranked from Within: Ranking Large Multimodal Models Without Labels [73.96543593298426]
  We show that uncertainty scores derived from softmax distributions provide a robust basis for ranking models across various tasks.<n>This facilitates the ranking of LMMs on unlabeled data, providing a practical approach for selecting models for diverse target domains without requiring manual annotation.
  arXiv  Detail & Related papers  (2024-12-09T13:05:43Z)
• Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning [12.80649024603656]
  This paper introduces data taggants, a novel non-backdoor dataset ownership verification technique. We validate our approach through comprehensive and realistic experiments on ImageNet1k using ViT and ResNet models with state-of-the-art training recipes.
  arXiv  Detail & Related papers  (2024-10-09T12:49:23Z)
• Training on the Benchmark Is Not All You Need [52.01920740114261]
  We propose a simple and effective data leakage detection method based on the contents of multiple-choice options.<n>Our method is able to work under gray-box conditions without access to model training data or weights.<n>We evaluate the degree of data leakage of 35 mainstream open-source LLMs on four benchmark datasets.
  arXiv  Detail & Related papers  (2024-09-03T11:09:44Z)
• Proving membership in LLM pretraining data via data watermarks [20.57538940552033]
  This work proposes using data watermarks to enable principled detection with only black-box model access. We study two watermarks: one that inserts random sequences, and another that randomly substitutes characters with Unicode lookalikes. We show that we can robustly detect hashes from BLOOM-176B's training data, as long as they occurred at least 90 times.
  arXiv  Detail & Related papers  (2024-02-16T18:49:27Z)
• Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking [54.40184736491652]
  We propose a backdoor-based watermarking approach that serves as a general framework for safeguarding public-available data. By inserting a small number of watermarking samples into the dataset, our approach enables the learning model to implicitly learn a secret function set by defenders. This hidden function can then be used as a watermark to track down third-party models that use the dataset illegally.
  arXiv  Detail & Related papers  (2023-03-20T21:54:30Z)
• Open-sourced Dataset Protection via Backdoor Watermarking [87.15630326131901]
  We propose a emphbackdoor embedding based dataset watermarking method to protect an open-sourced image-classification dataset. We use a hypothesis test guided method for dataset verification based on the posterior probability generated by the suspicious third-party model.
  arXiv  Detail & Related papers  (2020-10-12T16:16:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.