Watermarking for Proprietary Dataset Protection

• URL: http://arxiv.org/abs/2607.00325v1
• Date: Wed, 01 Jul 2026 01:55:14 GMT
• Title: Watermarking for Proprietary Dataset Protection
• Abstract summary: We argue that output watermarking techniques are the right gadget to make training membership tests for generative models more tractable.<n>We pit a watermark-based dataset inference approach head-to-head against traditional loss-based membership inference methods.
• Score: 67.79905448913145
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A growing body of literature suggests that training data membership inference problems are fundamentally hard tasks in modern language modeling settings. We argue that output watermarking techniques are the right gadget to make training membership tests for generative models more tractable, based on prior results showing that language models exhibit residual watermark "radioactivity" under partially watermarked training datasets. We pit a watermark-based dataset inference approach head-to-head against traditional loss-based membership inference methods and show that watermarking can achieve comparable membership detection performance when subset exposure is high enough, under an alternate set of assumptions.

Related papers

• Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio [58.612001688217056]
  Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization inconsistencies.<n>We propose an elegant solution for powerful and robust watermarking of synthetic audio.
  arXiv  Detail & Related papers  (2026-05-25T15:43:20Z)
• WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models [79.32764976020435]
  Digital watermarking is essential for securing generated images from diffusion models.<n>Previous watermark evaluation methods lack a unified framework for both residual and semantic watermarks.<n>We proposeLM, the first unified and interpretable evaluation framework for diffusion model image watermarking via vision-language models.
  arXiv  Detail & Related papers  (2026-01-29T12:14:32Z)
• In-Context Watermarks for Large Language Models [71.29952527565749]
  In-Context Watermarking (ICW) embeds watermarks into generated text solely through prompt engineering.<n>We investigate four ICW strategies at different levels of granularity, each paired with a tailored detection method.<n>Our experiments validate the feasibility of ICW as a model-agnostic, practical watermarking approach.
  arXiv  Detail & Related papers  (2025-05-22T17:24:51Z)
• Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge [31.766208360156906]
  Data watermarking in language models injects traceable signals, such as token sequences or stylistic patterns, into copyrighted text.<n>Previous data watermarking techniques primarily focus on effective memorization during pretraining.<n>We propose a novel data watermarking approach that injects plausible yet fictitious knowledge into training data using generated passages describing a fictitious entity.
  arXiv  Detail & Related papers  (2025-03-06T02:40:51Z)
• Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers [11.089926858383476]
  We propose model watermarking via passthrough layers, which are added to existing pre-trained networks.<n>Our method is fully task-agnostic, and can be applied to both classification and sequence-to-sequence tasks.<n>We show our method is robust to both downstream fine-tuning, fine-pruning, and layer removal attacks.
  arXiv  Detail & Related papers  (2024-12-17T05:46:50Z)
• Watermarking Training Data of Music Generation Models [6.902279764206365]
  We investigate whether audio watermarking techniques can be used to detect unauthorized usage of content.<n>We compare outputs generated by a model trained on watermarked data to a model trained on non-watermarked data.<n>Our results show that audio watermarking techniques, including some that are imperceptible to humans, can lead to noticeable shifts in the model's outputs.
  arXiv  Detail & Related papers  (2024-12-11T17:10:44Z)
• TokenMark: A Modality-Agnostic Watermark for Pre-trained Transformers [67.57928750537185]
  TokenMark is a robust, modality-agnostic, robust watermarking system for pre-trained models.<n>It embeds the watermark by fine-tuning the pre-trained model on a set of specifically permuted data samples.<n>It significantly improves the robustness, efficiency, and universality of model watermarking.
  arXiv  Detail & Related papers  (2024-03-09T08:54:52Z)
• Cross-Attention Watermarking of Large Language Models [8.704964543257246]
  New approach to linguistic watermarking of language models is presented. Information is imperceptibly inserted into the output text while preserving its readability and original meaning. Cross-attention mechanism is used to embed watermarks in the text during inference.
  arXiv  Detail & Related papers  (2024-01-12T09:39:50Z)
• Set-Membership Inference Attacks using Data Watermarking [21.69169876101301]
  We propose a set-membership inference attack for generative models using deep image watermarking techniques. Our empirical results demonstrate that the proposed watermarking technique is a principled approach for detecting the non-consensual use of image data in training generative models.
  arXiv  Detail & Related papers  (2023-06-22T06:47:56Z)
• 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)

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.