mlsanityData to 14 Oct 2026

Set-Membership Inference Attacks using Data Watermarking

arXiv 2307.15067 ↗First posted 22 Jun 2023cs.CV cs.CR cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

In this work, we propose a set-membership inference attack for generative models using deep image watermarking techniques. In particular, we demonstrate how conditional sampling from a generative model can reveal the watermark that was injected into parts of the training data. 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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 13 of its 17 references that are in the map. First posted on arXiv 22 Jun 2023.

Builds on

13 of 17 references.

References · 13

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  5. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  6. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  7. 2021Membership Inference Attacks From First Principlescited by 878
  8. 2023Extracting Training Data from Diffusion Modelscited by 732
  9. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 424
  10. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 265
  11. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 201
  12. 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?cited by 136
1 more
  1. 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11

Similar, not cited

Close in wording, no citation either way

  1. 2026Watermarking for Proprietary Dataset Protection
  2. 2023Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models
  3. 2026Attribute-based Undetectable Watermarking for Generative AI Models
  4. 2025Spread them Apart: Towards Robust Watermarking of Generated Content
  5. 2022Generative Models with Information-Theoretic Protection Against Membership Inference Attacks
  6. 2023Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
  7. 2023Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
  8. 2021Evaluating the Robustness of Trigger Set-Based Watermarks Embedded in Deep Neural Networks