mlsanityData to 14 Oct 2026

Evaluating Adversarial Protections for Diffusion Personalization: A Comprehensive Study

arXiv 2507.03953 ↗First posted 5 Jul 2025cs.CV cs.AIcited by 3

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

Abstract (arXiv)

With the increasing adoption of diffusion models for image generation and personalization, concerns regarding privacy breaches and content misuse have become more pressing. In this study, we conduct a comprehensive comparison of eight perturbation based protection methods: AdvDM, ASPL, FSGM, MetaCloak, Mist, PhotoGuard, SDS, and SimAC--across both portrait and artwork domains. These methods are evaluated under varying perturbation budgets, using a range of metrics to assess visual imperceptibility and protective efficacy. Our results offer practical guidance for method selection. Code is available at: https://github.com/vkeilo/DiffAdvPerturbationBench.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 22 of its 28 references that are in the map. First posted on arXiv 5 Jul 2025.

Builds on

22 of 28 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based Customization31 May
  2. 2023SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models13 Dec
  3. 2023MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning22 Nov
  4. 2023Toward effective protection against diffusion based mimicry through score distillation2 Oct
  5. 2023Mist: Towards Improved Adversarial Examples for Diffusion Models22 May
  6. 2023Anti-DreamBooth: Protecting users from personalized text-to-image synthesis27 Mar
  7. 2023Raising the Cost of Malicious AI-Powered Image Editing13 Feb
  8. 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples9 Feb

Other references · 14

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  7. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  8. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
  9. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  10. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  11. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  12. 2015Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Featurecited by 182
2 more
  1. 2020Defending against GAN-based Deepfake Attacks via Transformation-aware Adversarial Facescited by 21
  2. 2024DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Modelscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026IPV-Bench: Benchmarking Image Protection Methods under Diverse Image-to-Video Generation Scenarioscited by 3
  2. 2026Representation Learning in Diffusion and Flow-based Model: An Application Aspectcited by 0
  3. 2026Anti-Persona: Disrupting Unauthorized Identity Binding and Recognition in Personalized Vision--Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation
  2. 2023Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
  3. 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
  4. 2024Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models
  5. 2025Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
  6. 2025Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification
  7. 2024Visual-Friendly Concept Protection via Selective Adversarial Perturbations
  8. 2026Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations?