mlsanityData to 14 Oct 2026

Typology of Risks of Generative Text-to-Image Models

arXiv 2307.05543 ↗First posted 8 Jul 2023cs.CYcited by 55

Not on the map. Why?

Abstract (arXiv)

This paper investigates the direct risks and harms associated with modern text-to-image generative models, such as DALL-E and Midjourney, through a comprehensive literature review. While these models offer unprecedented capabilities for generating images, their development and use introduce new types of risk that require careful consideration. Our review reveals significant knowledge gaps concerning the understanding and treatment of these risks despite some already being addressed. We offer a taxonomy of risks across six key stakeholder groups, inclusive of unexplored issues, and suggest future research directions. We identify 22 distinct risk types, spanning issues from data bias to malicious use. The investigation presented here is intended to enhance the ongoing discourse on responsible model development and deployment. By highlighting previously overlooked risks and gaps, it aims to shape subsequent research and governance initiatives, guiding them toward the responsible, secure, and ethically conscious evolution of text-to-image models.

Key facts. Cited by 55 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Jul 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 27; 2025: 15; 2026: 8.

55 papers.

Sort:

By area:

  1. 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scalecited by 268
  2. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 157
  3. 2024Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigationcited by 66
  4. 2024SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Modelscited by 66
  5. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
  6. 2024Design Principles for Generative AI Applicationscited by 57
  7. 2024An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevancecited by 36
  8. 2024AI Safety in Generative AI Large Language Models: A Surveycited by 33
  9. 2024Beyond Aesthetics: Cultural Competence in Text-to-Image Modelscited by 30
  10. 2024Two Types of AI Existential Risk: Decisive and Accumulativecited by 22
  11. 2024Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusioncited by 22
  12. 2024Mapping the Ethics of Generative AI: A Comprehensive Scoping Reviewcited by 19
38 more
  1. 2024Holistic Safety and Responsibility Evaluations of Advanced AI Modelscited by 19
  2. 2023IMMA: Immunizing text-to-image Models against Malicious Adaptationcited by 18
  3. 2023Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Modelscited by 16
  4. 2023Quantifying Bias in Text-to-Image Generative Modelscited by 16
  5. 2024Epistemic Injustice in Generative AIcited by 16
  6. 2024Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help Youcited by 15
  7. 2024Harm Amplification in Text-to-Image Modelscited by 15
  8. 2024Who's in and who's out? A case study of multimodal CLIP-filtering in DataCompcited by 15
  9. 2024Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learningcited by 12
  10. 2024Exploring the Use of Abusive Generative AI Models on Civitaicited by 10
  11. 2025TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Storiescited by 10
  12. 2025Erased or Dormant? Rethinking Concept Erasure Through Reversibilitycited by 9
  13. 2024FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generationcited by 7
  14. 2025Adoption of Watermarking for Generative AI Systems in Practice and Implications under the new EU AI Actcited by 7
  15. 2024Thematic Analysis with Open-Source Generative AI and Machine Learning: A New Method for Inductive Qualitative Codebook Developmentcited by 6
  16. 2024From Silos to Systems: Process-Oriented Hazard Analysis for AI Systemscited by 6
  17. 2025POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generationcited by 6
  18. 2025MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Modelscited by 5
  19. 2025Fit for Purpose? Deepfake Detection in the Real Worldcited by 4
  20. 2024Civiverse: A Dataset for Analyzing User Engagement with Open-Source Text-to-Image Modelscited by 3
  21. 2024Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimizationcited by 2
  22. 2025Toward Effective AI Governance: A Review of Principlescited by 2
  23. 2025SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editingcited by 2
  24. 2025Smudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprintscited by 2
  25. 2026Selective Fine-Tuning for Targeted and Robust Concept Unlearningcited by 2
  26. 2026Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scalescited by 2
  27. 2024Taxonomy to Regulation: A (Geo)Political Taxonomy for AI Risks and Regulatory Measures in the EU AI Actcited by 1
  28. 2024Controllable Image Generation with Composed Parallel Token Predictioncited by 1
  29. 2024Harnessing Federated Generative Learning for Green and Sustainable Internet of Thingscited by 1
  30. 2024Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Modelscited by 1
  31. 2025RusCode: Russian Cultural Code Benchmark for Text-to-Image Generationcited by 1
  32. 2025LLMs Behind the Scenes: Enabling Narrative Scene Illustrationcited by 1
  33. 2025NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generationcited by 1
  34. 2026Safe Autoregressive Image Generation with Iterative Self-Improving Codebookscited by 1
  35. 2026Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detectioncited by 1
  36. 2023Approaches to Generative Artificial Intelligence, A Social Justice Perspectivecited by 0
  37. 2025Kaleidoscope Gallery: Exploring Ethics and Generative AI Through Artcited by 0
  38. 2025From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Modelscited by 0

50 most cited of 55 All 55 (JSON)