# Typology of Risks of Generative Text-to-Image Models

arXiv: https://arxiv.org/abs/2307.05543 · HTML: https://mlsanity.com/paper/2307.05543/

## Key facts

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

## Built on by (most cited first, 30 of 55)

- [UltraEdit: Instruction-based Fine-Grained Image Editing at Scale](https://mlsanity.com/paper/2407.05282/) (2024)
- [Sociotechnical Safety Evaluation of Generative AI Systems](https://mlsanity.com/paper/2310.11986/) (2023)
- [Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation](https://mlsanity.com/paper/2404.01030/) (2024)
- [SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models](https://mlsanity.com/paper/2404.06666/) (2024)
- [A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)](https://mlsanity.com/paper/2404.00579/) (2024)
- [Design Principles for Generative AI Applications](https://mlsanity.com/paper/2401.14484/) (2024)
- [An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance](https://mlsanity.com/paper/2404.01247/) (2024)
- [AI Safety in Generative AI Large Language Models: A Survey](https://mlsanity.com/paper/2407.18369/) (2024)
- [Beyond Aesthetics: Cultural Competence in Text-to-Image Models](https://mlsanity.com/paper/2407.06863/) (2024)
- [Two Types of AI Existential Risk: Decisive and Accumulative](https://mlsanity.com/paper/2401.07836/) (2024)
- [Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion](https://mlsanity.com/paper/2408.12692/) (2024)
- [Mapping the Ethics of Generative AI: A Comprehensive Scoping Review](https://mlsanity.com/paper/2402.08323/) (2024)
- [Holistic Safety and Responsibility Evaluations of Advanced AI Models](https://mlsanity.com/paper/2404.14068/) (2024)
- [IMMA: Immunizing text-to-image Models against Malicious Adaptation](https://mlsanity.com/paper/2311.18815/) (2023)
- [Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models](https://mlsanity.com/paper/2310.01929/) (2023)
- [Quantifying Bias in Text-to-Image Generative Models](https://mlsanity.com/paper/2312.13053/) (2023)
- [Epistemic Injustice in Generative AI](https://mlsanity.com/paper/2408.11441/) (2024)
- [Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You](https://mlsanity.com/paper/2401.16092/) (2024)
- [Harm Amplification in Text-to-Image Models](https://mlsanity.com/paper/2402.01787/) (2024)
- [Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp](https://mlsanity.com/paper/2405.08209/) (2024)
- [Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning](https://mlsanity.com/paper/2407.12164/) (2024)
- [Exploring the Use of Abusive Generative AI Models on Civitai](https://mlsanity.com/paper/2407.12876/) (2024)
- [TALES: A Taxonomy and Analysis of Cultural Representations in LLM-generated Stories](https://mlsanity.com/paper/2511.21322/) (2025)
- [Erased or Dormant? Rethinking Concept Erasure Through Reversibility](https://mlsanity.com/paper/2505.16174/) (2025)
- [FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation](https://mlsanity.com/paper/2410.18615/) (2024)
- [Adoption of Watermarking for Generative AI Systems in Practice and Implications under the new EU AI Act](https://mlsanity.com/paper/2503.18156/) (2025)
- [Thematic Analysis with Open-Source Generative AI and Machine Learning: A New Method for Inductive Qualitative Codebook Development](https://mlsanity.com/paper/2410.03721/) (2024)
- [From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems](https://mlsanity.com/paper/2410.22526/) (2024)
- [POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generation](https://mlsanity.com/paper/2504.13392/) (2025)
- [MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models](https://mlsanity.com/paper/2509.10569/) (2025)

## 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.