Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking

• URL: http://arxiv.org/abs/2510.02962v1
• Date: Fri, 03 Oct 2025 12:53:02 GMT
• Title: Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking
• Authors: Jingqi Zhang, Ruibo Chen, Yingqing Yang, Peihua Mai, Heng Huang, Yan Pang,
• Abstract summary: We propose TRACE, a framework for fully black-box detection of copyrighted dataset usage in large language models.<n>textttTRACE rewrites datasets with distortion-free watermarks guided by a private key.<n>Across diverse datasets and model families, TRACE consistently achieves significant detections.
• Score: 51.74368870268278
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are increasingly fine-tuned on smaller, domain-specific datasets to improve downstream performance. These datasets often contain proprietary or copyrighted material, raising the need for reliable safeguards against unauthorized use. Existing membership inference attacks (MIAs) and dataset-inference methods typically require access to internal signals such as logits, while current black-box approaches often rely on handcrafted prompts or a clean reference dataset for calibration, both of which limit practical applicability. Watermarking is a promising alternative, but prior techniques can degrade text quality or reduce task performance. We propose TRACE, a practical framework for fully black-box detection of copyrighted dataset usage in LLM fine-tuning. \texttt{TRACE} rewrites datasets with distortion-free watermarks guided by a private key, ensuring both text quality and downstream utility. At detection time, we exploit the radioactivity effect of fine-tuning on watermarked data and introduce an entropy-gated procedure that selectively scores high-uncertainty tokens, substantially amplifying detection power. Across diverse datasets and model families, TRACE consistently achieves significant detections (p<0.05), often with extremely strong statistical evidence. Furthermore, it supports multi-dataset attribution and remains robust even after continued pretraining on large non-watermarked corpora. These results establish TRACE as a practical route to reliable black-box verification of copyrighted dataset usage. We will make our code available at: https://github.com/NusIoraPrivacy/TRACE.

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)
• Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs [67.0310240737424]
  We introduce a novel approach to safeguard the ownership of text datasets and effectively detect unauthorized use by the RA-LLMs.<n>Our approach preserves the original data completely unchanged while protecting it by inserting specifically designed canary documents into the IP dataset.<n>During the detection process, unauthorized usage is identified by querying the canary documents and analyzing the responses of RA-LLMs.
  arXiv  Detail & Related papers  (2025-02-15T04:56:45Z)
• 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)
• Detecting Dataset Abuse in Fine-Tuning Stable Diffusion Models for Text-to-Image Synthesis [3.8809673918404246]
  dataset watermarking framework designed to detect unauthorized usage and trace data leaks. We present a dataset watermarking framework designed to detect unauthorized usage and trace data leaks.
  arXiv  Detail & Related papers  (2024-09-27T16:34:48Z)
• FreqyWM: Frequency Watermarking for the New Data Economy [8.51675079658644]
  We present a novel technique for modulating the appearance frequency of a few tokens within a dataset for encoding an invisible watermark. We develop optimal as well as fast algorithms for creating and verifying such watermarks.
  arXiv  Detail & Related papers  (2023-12-27T12:17:59Z)
• Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand [96.26251471253823]
  backdoor-based dataset ownership verification (DOV) is currently the only feasible approach to protect the copyright of open-source datasets. We make watermarked models (trained on the protected dataset) correctly classify some hard' samples that will be misclassified by the benign model.
  arXiv  Detail & Related papers  (2023-10-09T11:23:05Z)
• 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)
• Black-box Dataset Ownership Verification via Backdoor Watermarking [67.69308278379957]
  We formulate the protection of released datasets as verifying whether they are adopted for training a (suspicious) third-party model. We propose to embed external patterns via backdoor watermarking for the ownership verification to protect them. Specifically, we exploit poison-only backdoor attacks ($e.g.$, BadNets) for dataset watermarking and design a hypothesis-test-guided method for dataset verification.
  arXiv  Detail & Related papers  (2022-08-04T05:32:20Z)
• On the Effectiveness of Dataset Watermarking in Adversarial Settings [14.095584034871658]
  We investigate a proposed data provenance method, radioactive data, to assess if it can be used to demonstrate ownership of (image) datasets used to train machine learning (ML) models. We show that radioactive data can effectively survive model extraction attacks, which raises the possibility that it can be used for ML model ownership verification robust against model extraction.
  arXiv  Detail & Related papers  (2022-02-25T05:51:53Z)

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.