# SafeGen: Embedding Ethical Safeguards in Text-to-Image Generation

arXiv: https://arxiv.org/abs/2512.12501 · HTML: https://mlsanity.com/paper/2512.12501/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 14 Dec 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild](https://mlsanity.com/paper/1906.02569/) (2019)
- [SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models](https://mlsanity.com/paper/2404.06666/) (2024)
- [Typology of Risks of Generative Text-to-Image Models](https://mlsanity.com/paper/2307.05543/) (2023)
- [A Trade-off-centered Framework of Content Moderation](https://mlsanity.com/paper/2206.03450/) (2022)
- [Imagining the Far East: Exploring Perceived Biases in AI-Generated Images of East Asian Women](https://mlsanity.com/paper/2504.04865/) (2025)
- [Ethics and Technical Aspects of Generative AI Models in Digital Content Creation](https://mlsanity.com/paper/2412.16389/) (2024)
- [A Portrait of Emotion: Empowering Self-Expression through AI-Generated Art](https://mlsanity.com/paper/2304.13324/) (2023)

## Abstract (arXiv)

Generative Artificial Intelligence (AI) has created unprecedented opportunities for creative expression, education, and research. Text-to-image systems such as DALL.E, Stable Diffusion, and Midjourney can now convert ideas into visuals within seconds, but they also present a dual-use dilemma, raising critical ethical concerns: amplifying societal biases, producing high-fidelity disinformation, and violating intellectual property. This paper introduces SafeGen, a framework that embeds ethical safeguards directly into the text-to-image generation pipeline, grounding its design in established principles for Trustworthy AI. SafeGen integrates two complementary components: BGE-M3, a fine-tuned text classifier that filters harmful or misleading prompts, and Hyper-SD, an optimized diffusion model that produces high fidelity, semantically aligned images. Built on a curated multilingual (English- Vietnamese) dataset and a fairness-aware training process, SafeGen demonstrates that creative freedom and ethical responsibility can be reconciled within a single workflow. Quantitative evaluations confirm its effectiveness, with Hyper-SD achieving IS = 3.52, FID = 22.08, and SSIM = 0.79, while BGE-M3 reaches an F1-Score of 0.81. An ablation study further validates the importance of domain-specific fine-tuning for both modules. Case studies illustrate SafeGen's practical impact in blocking unsafe prompts, generating inclusive teaching materials, and reinforcing academic integrity.