# Watermarking for Proprietary Dataset Protection

arXiv: https://arxiv.org/abs/2607.00325 · HTML: https://mlsanity.com/paper/2607.00325/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 19 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [Detecting Pretraining Data from Large Language Models](https://mlsanity.com/paper/2310.16789/) (2023)
- [Do Membership Inference Attacks Work on Large Language Models?](https://mlsanity.com/paper/2402.07841/) (2024)
- [Datamodels: Predicting Predictions from Training Data](https://mlsanity.com/paper/2202.00622/) (2022)
- [Mark My Words: Analyzing and Evaluating Language Model Watermarks](https://mlsanity.com/paper/2312.00273/) (2023)
- [Watermarking Makes Language Models Radioactive](https://mlsanity.com/paper/2402.14904/) (2024)
- [Extracting memorized pieces of (copyrighted) books from open-weight language models](https://mlsanity.com/paper/2505.12546/) (2025)
- [Exploring the limits of strong membership inference attacks on large language models](https://mlsanity.com/paper/2505.18773/) (2025)
- [Language Models May Verbatim Complete Text They Were Not Explicitly Trained On](https://mlsanity.com/paper/2503.17514/) (2025)
- [Detecting Benchmark Contamination Through Watermarking](https://mlsanity.com/paper/2502.17259/) (2025)
- [Antidistillation Fingerprinting](https://mlsanity.com/paper/2602.03812/) (2026)
- [How Good is Post-Hoc Watermarking With Language Model Rephrasing?](https://mlsanity.com/paper/2512.16904/) (2025)

## Abstract (arXiv)

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.