mlsanityData to 7 Oct 2026

Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability

arXiv 2401.07087 ↗First posted 13 Jan 2024cs.CV cs.CR cs.LGcited by 5

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

Abstract (arXiv)

Recently, many studies utilized adversarial examples (AEs) to raise the cost of malicious image editing and copyright violation powered by latent diffusion models (LDMs). Despite their successes, a few have studied the surrogate model they used to generate AEs. In this paper, from the perspective of adversarial transferability, we investigate how the surrogate model's property influences the performance of AEs for LDMs. Specifically, we view the time-step sampling in the Monte-Carlo-based (MC-based) adversarial attack as selecting surrogate models. We find that the smoothness of surrogate models at different time steps differs, and we substantially improve the performance of the MC-based AEs by selecting smoother surrogate models. In the light of the theoretical framework on adversarial transferability in image classification, we also conduct a theoretical analysis to explain why smooth surrogate models can also boost AEs for LDMs.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 26 of its 28 references that are in the map. First posted on arXiv 13 Jan 2024.

Builds on

26 of 28 references.

Closest ancestors · 8

Same direction, newest first

  1. 2023SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models13 Dec
  2. 2023Toward effective protection against diffusion based mimicry through score distillation2 Oct
  3. 2023On the Robustness of Latent Diffusion Models14 Jun
  4. 2023Mist: Towards Improved Adversarial Examples for Diffusion Models22 May
  5. 2023JPEG Compressed Images Can Bypass Protections Against AI Editing5 Apr
  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 · 18

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  6. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  7. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  8. 2017Countering Adversarial Images using Input Transformationscited by 517
  9. 2021Adversarial Examples Make Strong Poisonscited by 115
  10. 2020On Success and Simplicity: A Second Look at Transferable Targeted Attackscited by 89
  11. 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
  12. 2018Learning Transferable Adversarial Examples via Ghost Networkscited by 69
6 more
  1. 2023An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferabilitycited by 42
  2. 2022LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinitycited by 39
  3. 2021TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothnesscited by 37
  4. 2021A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attackscited by 33
  5. 2023Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabilitycited by 32
  6. 2021Contrastive Language-Image Pre-training for the Italian Languagecited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 0; 2026: 1.

5 papers.

  1. 2024Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policiescited by 17
  2. 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Modelscited by 14
  3. 2024Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Thinkcited by 10
  4. 2024Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generationcited by 2
  5. 2026VOID: Defeating Unauthorized Mimicry in Latent Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
  2. 2024Adversarial Examples are Misaligned in Diffusion Model Manifolds
  3. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey
  4. 2025Towards more transferable adversarial attack in black-box manner
  5. 2025Beyond Classification: Evaluating Diffusion Denoised Smoothing for Security-Utility Trade off
  6. 2023Adversarial defense based on distribution transfer
  7. 2023Improving Adversarial Transferability by Stable Diffusion
  8. 2025A Unified Framework for Stealthy Adversarial Generation via Latent Optimization and Transferability Enhancement