mlsanityData to 14 Oct 2026

Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models

arXiv 2509.22723 ↗First posted 25 Sep 2025cs.CR cs.CVcited by 3

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

Abstract (arXiv)

Diffusion models (DMs) have been investigated in various domains due to their ability to generate high-quality data, thereby attracting significant attention. However, similar to traditional deep learning systems, there also exist potential threats to DMs. To provide advanced and comprehensive insights into safety, ethics, and trust in DMs, this survey comprehensively elucidates its framework, threats, and countermeasures. Each threat and its countermeasures are systematically examined and categorized to facilitate thorough analysis. Furthermore, we introduce specific examples of how DMs are used, what dangers they might bring, and ways to protect against these dangers. Finally, we discuss key lessons learned, highlight open challenges related to DM security, and outline prospective research directions in this critical field. This work aims to accelerate progress not only in the technical capabilities of generative artificial intelligence but also in the maturity and wisdom of its application.

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 105 of its 122 references that are in the map. First posted on arXiv 25 Sep 2025.

Builds on

105 of 122 references.

Closest ancestors · 46

Same direction, newest first

  1. 2025Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models9 Aug
  2. 2025Frequency-Calibrated Membership Inference Attacks on Medical Image Diffusion Models17 Jun
  3. 2025Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models12 Mar
  4. 2024Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images13 Dec
  5. 2024AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models28 Oct
  6. 2024Dual-Model Defense: Safeguarding Diffusion Models from Membership Inference Attacks through Disjoint Data Splitting22 Oct
  7. 2024SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation16 Oct
  8. 2024SIDE: Surrogate Conditional Data Extraction from Diffusion Models3 Oct
  9. 2024Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey26 Sep
  10. 2024TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors9 Sep
  11. 2024Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks28 Aug
  12. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey6 Aug
34 more
  1. 2024Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models31 Jul
  2. 2024Unveiling Structural Memorization: Structural Membership Inference Attack for Text-to-Image Diffusion Models18 Jul
  3. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey10 Jul
  4. 2024T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models5 Jul
  5. 2024Gradient Inversion of Federated Diffusion Models30 May
  6. 2024Towards Black-Box Membership Inference Attack for Diffusion Models25 May
  7. 2024Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy23 May
  8. 2024Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models15 Apr
  9. 2024Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models2 Apr
  10. 2024UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models1 Apr
  11. 2024Model Will Tell: Training Membership Inference for Diffusion Models13 Mar
  12. 2024Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective28 Feb
  13. 2024ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation23 Feb
  14. 2024Privacy-Preserving Low-Rank Adaptation against Membership Inference Attacks for Latent Diffusion Models19 Feb
  15. 2023Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model18 Dec
  16. 2023Black-box Membership Inference Attacks against Fine-tuned Diffusion Models13 Dec
  17. 2023Membership Inference Attacks on Diffusion Models via Quantile Regression8 Dec
  18. 2023MMA-Diffusion: MultiModal Attack on Diffusion Models29 Nov
  19. 2023Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models30 Oct
  20. 2023To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now18 Oct
  21. 2023FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models3 Oct
  22. 2023On Copyright Risks of Text-to-Image Diffusion Models15 Sep
  23. 2023VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models12 Jun
  24. 2023PriSampler: Mitigating Property Inference of Diffusion Models8 Jun
  25. 2023An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization26 May
  26. 2023Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models23 May
  27. 2023Watermarking Diffusion Model21 May
  28. 2023SneakyPrompt: Jailbreaking Text-to-image Generative Models20 May
  29. 2023Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning7 May
  30. 2023A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion29 Mar
  31. 2023TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets10 Mar
  32. 2023Membership Inference Attacks against Diffusion Models7 Feb
  33. 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?2 Feb
  34. 2023Extracting Training Data from Diffusion Models30 Jan

Other references · 59

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  5. 2016Deep Learning with Differential Privacycited by 2,728
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  7. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,045
  8. 2022Diffusion Models in Vision: A Surveycited by 1,015
  9. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  10. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 781
  11. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  12. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
38 more
  1. 2020Backdoor Learning: A Surveycited by 426
  2. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 424
  3. 2023Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Modelscited by 359
  4. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 238
  5. 2023TextDiffuser: Diffusion Models as Text Painterscited by 229
  6. 2023Understanding and Mitigating Copying in Diffusion Modelscited by 209
  7. 2023Fair Diffusion: Instructing Text-to-Image Generation Models on Fairnesscited by 151
  8. 2023On Memorization in Diffusion Modelscited by 125
  9. 2023MedSegDiff-V2: Diffusion based Medical Image Segmentation with Transformercited by 124
  10. 2023On Provable Copyright Protection for Generative Modelscited by 98
  11. 2024Detecting, Explaining, and Mitigating Memorization in Diffusion Modelscited by 95
  12. 2023Finetuning Text-to-Image Diffusion Models for Fairnesscited by 92
  13. 2024Understanding Hallucinations in Diffusion Models through Mode Interpolationcited by 91
  14. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecastingcited by 88
  15. 2023Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Modelscited by 83
  16. 2024Latent Guard: a Safety Framework for Text-to-image Generationcited by 71
  17. 2022Membership Inference Attacks Against Text-to-image Generation Modelscited by 69
  18. 2023On the Generalization Properties of Diffusion Modelscited by 68
  19. 2024Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attentioncited by 58
  20. 2023Prompt Stealing Attacks Against Text-to-Image Generation Modelscited by 51
  21. 2024Direct Unlearning Optimization for Robust and Safe Text-to-Image Modelscited by 50
  22. 2023Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Modelscited by 40
  23. 2024Perception-guided Jailbreak against Text-to-Image Modelscited by 40
  24. 2025DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Modelscited by 40
  25. 2023Security and Privacy on Generative Data in AIGC: A Surveycited by 34
  26. 2021Property Inference Attacks Against GANscited by 33
  27. 2023PromptCARE: Prompt Copyright Protection by Watermark Injection and Verificationcited by 32
  28. 2024Diffusion Models for Audio Restorationcited by 32
  29. 2021Measuring Fairness in Generative Modelscited by 31
  30. 2023A Unified Framework for U-Net Design and Analysiscited by 27
  31. 2023Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Searchcited by 25
  32. 2022Trusted AI in Multi-agent Systems: An Overview of Privacy and Security for Distributed Learningcited by 22
  33. 2024Tackling Structural Hallucination in Image Translation with Local Diffusioncited by 21
  34. 2024AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusioncited by 20
  35. 2024Diffusion-Based Visual Art Creation: A Survey and New Perspectivescited by 17
  36. 2024HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Modelscited by 16
  37. 2023Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learningcited by 14
  38. 2024Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesiscited by 11

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformerscited by 2
  2. 2026Tuning Just Enough: Lightweight Backdoor Attacks on Multi-Encoder Diffusion Modelscited by 0
  3. 2026A Survey on Adversarial Attacks and Defenses for Diffusion Models Across Multiple Modalitiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook
  2. 2023Diffusion-C: Unveiling the Generative Challenges of Diffusion Models through Corrupted Data
  3. 2024CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making
  4. 2023Data Forensics in Diffusion Models: A Systematic Analysis of Membership Privacy
  5. 2025A Survey on Diffusion Models for Anomaly Detection
  6. 2023From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
  7. 2023Toward effective protection against diffusion based mimicry through score distillation
  8. 2026Concept-Level Risk and Calibration for Governance in Diffusion Foundation Models