mlsanityData to 7 Oct 2026

Targeted Image Reconstruction by Sampling Pre-trained Diffusion Model

arXiv 2301.07557 ↗First posted 18 Jan 2023cs.LG cs.AI cs.CRcited by 1

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

A trained neural network model contains information on the training data. Given such a model, malicious parties can leverage the "knowledge" in this model and design ways to print out any usable information (known as model inversion attack). Therefore, it is valuable to explore the ways to conduct a such attack and demonstrate its severity. In this work, we proposed ways to generate a data point of the target class without prior knowledge of the exact target distribution by using a pre-trained diffusion model.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 12 of its 14 references that are in the map. First posted on arXiv 18 Jan 2023.

Builds on

12 of 14 references.

References · 12

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2022Generative Adversarial Networkscited by 5,603
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  9. 2019An Introduction to Variational Autoencoderscited by 997
  10. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  11. 2022Reconstructing Training Data with Informed Adversariescited by 143
  12. 2022Few-shot Image Generation with Diffusion Modelscited by 21

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Modelcited by 14

Similar, not cited

Close in wording, no citation either way

  1. 2024Model Inversion Attacks Through Target-Specific Conditional Diffusion Models
  2. 2024Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model
  3. 2024Exploring User-level Gradient Inversion with a Diffusion Prior
  4. 2024Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction
  5. 2025Explore the vulnerability of black-box models via diffusion models
  6. 2023Rethinking Model Inversion Attacks With Patch-Wise Reconstruction
  7. 2025Towards Irreversible Machine Unlearning for Diffusion Models
  8. 2025DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models