mlsanityData to 7 Oct 2026

Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking

arXiv 2403.14778 ↗First posted 21 Mar 2024cs.CV eess.IVcited by 0

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

Abstract (arXiv)

In Virtual Reality (VR), adversarial attack remains a significant security threat. Most deep learning-based methods for physical and digital adversarial attacks focus on enhancing attack performance by crafting adversarial examples that contain large printable distortions that are easy for human observers to identify. However, attackers rarely impose limitations on the naturalness and comfort of the appearance of the generated attack image, resulting in a noticeable and unnatural attack. To address this challenge, we propose a framework to incorporate style transfer to craft adversarial inputs of natural styles that exhibit minimal detectability and maximum natural appearance, while maintaining superior attack capabilities.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 5 of its 7 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

5 of 7 references.

References · 5

  1. 2017NIMA: Neural Image Assessmentcited by 387
  2. 2023TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessmentcited by 220
  3. 2021No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistencycited by 165
  4. 2020SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbationscited by 50
  5. 2023Physical Adversarial Attacks on Deep Neural Networks for Traffic Sign Recognition: A Feasibility Studycited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Survey on Adversarial Attacks and Defenses for Diffusion Models Across Multiple Modalities
  2. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attack
  3. 2025AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks
  4. 2023Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector
  5. 2024Adversarial Examples are Misaligned in Diffusion Model Manifolds
  6. 2023Content-based Unrestricted Adversarial Attack
  7. 2023Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models
  8. 2025Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models