mlsanityData to 14 Oct 2026

On the Robustness of Latent Diffusion Models

arXiv 2306.08257 ↗First posted 14 Jun 2023cs.CV cs.CRcited by 21

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

Abstract (arXiv)

Latent diffusion models achieve state-of-the-art performance on a variety of generative tasks, such as image synthesis and image editing. However, the robustness of latent diffusion models is not well studied. Previous works only focus on the adversarial attacks against the encoder or the output image under white-box settings, regardless of the denoising process. Therefore, in this paper, we aim to analyze the robustness of latent diffusion models more thoroughly. We first study the influence of the components inside latent diffusion models on their white-box robustness. In addition to white-box scenarios, we evaluate the black-box robustness of latent diffusion models via transfer attacks, where we consider both prompt-transfer and model-transfer settings and possible defense mechanisms. However, all these explorations need a comprehensive benchmark dataset, which is missing in the literature. Therefore, to facilitate the research of the robustness of latent diffusion models, we propose two automatic dataset construction pipelines for two kinds of image editing models and release the whole dataset. Our code and dataset are available at urlhttps://github.com/jpzhang1810/LDM-Robustness.

Key facts. Cited by 21 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 23 of its 29 references that are in the map. First posted on arXiv 14 Jun 2023.

Builds on

23 of 29 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion29 Mar
  2. 2023Raising the Cost of Malicious AI-Powered Image Editing13 Feb

Other references · 21

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2022Training language models to follow instructions with human feedbackcited by 15,971
  7. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  9. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  11. 2022Generative Adversarial Networkscited by 5,627
  12. 2016Improved Techniques for Training GANscited by 2,970
9 more
  1. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  2. 2016Adversarial examples in the physical worldcited by 1,769
  3. 2017Mitigating Adversarial Effects Through Randomizationcited by 383
  4. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  5. 2018Certified Adversarial Robustness with Additive Noisecited by 180
  6. 2018Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examplescited by 99
  7. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 93
  8. 2023Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularizationcited by 42
  9. 2023Improving the Transferability of Adversarial Samples by Path-Augmented Methodcited by 36

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 10; 2025: 4; 2026: 2.

21 papers.

Sort:

By area:

  1. 2023MMA-Diffusion: MultiModal Attack on Diffusion Modelscited by 194
  2. 2023Toward effective protection against diffusion based mimicry through score distillationcited by 65
  3. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  4. 2024Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editingcited by 21
  5. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  6. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 13
  7. 2024Dormant: Defending against Pose-driven Human Image Animationcited by 11
  8. 2024ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbationcited by 10
  9. 2024Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Thinkcited by 10
  10. 2025PLA: Prompt Learning Attack against Text-to-Image Generative Modelscited by 9
  11. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  12. 2024FaceShield: Defending Facial Image against Deepfake Threatscited by 8
9 more
  1. 2026CtrlAttack: A Unified Attack on World-Model Control in Diffusion Modelscited by 7
  2. 2024Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferabilitycited by 5
  3. 2025T2VAttack: Adversarial Attack on Text-to-Video Diffusion Modelscited by 5
  4. 2023Backpropagation Path Search On Adversarial Transferabilitycited by 4
  5. 2024Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generationcited by 2
  6. 2023Trustworthy Large Models in Vision: A Surveycited by 0
  7. 2025Cross-Cultural Fashion Design via Interactive Large Language Models and Diffusion Modelscited by 0
  8. 2025Security Risk of Misalignment between Text and Image in Multi-modal Modelcited by 0
  9. 2026VOID: Defeating Unauthorized Mimicry in Latent Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating Robustness in Latent Diffusion Models via Embedding Level Augmentation
  2. 2025CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
  3. 2025Demystifying Adversarial Robustness in Diffusion Models: Compression, Randomness, and Geometry
  4. 2026Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models
  5. 2024Adversarial Examples are Misaligned in Diffusion Model Manifolds
  6. 2024Enabling Local Editing in Diffusion Models by Joint and Individual Component Analysis
  7. 2024A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse
  8. 2025Diffusion Models are Robust Pretrainers