# SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing

arXiv: https://arxiv.org/abs/2510.24820 · HTML: https://mlsanity.com/paper/2510.24820/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security.
- Builds on 29 of its 35 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Placed in

- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?](https://mlsanity.com/paper/2310.10012/) (2023)
- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (2023)
- [Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts](https://mlsanity.com/paper/2309.06135/) (2023)
- [SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation](https://mlsanity.com/paper/2410.12761/) (2024)
- [Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models](https://mlsanity.com/paper/2404.02928/) (2024)
- [Latent Guard: a Safety Framework for Text-to-image Generation](https://mlsanity.com/paper/2404.08031/) (2024)
- [GuardT2I: Defending Text-to-Image Models from Adversarial Prompts](https://mlsanity.com/paper/2403.01446/) (2024)
- [Typology of Risks of Generative Text-to-Image Models](https://mlsanity.com/paper/2307.05543/) (2023)
- [UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images](https://mlsanity.com/paper/2405.03486/) (2024)
- [T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation](https://mlsanity.com/paper/2501.12612/) (2025)
- [Universal Prompt Optimizer for Safe Text-to-Image Generation](https://mlsanity.com/paper/2402.10882/) (2024)
- [MLLM-as-a-Judge for Image Safety without Human Labeling](https://mlsanity.com/paper/2501.00192/) (2024)
- [T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models](https://mlsanity.com/paper/2504.15512/) (2025)
- [PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models](https://mlsanity.com/paper/2501.03544/) (2025)
- [Harm Amplification in Text-to-Image Models](https://mlsanity.com/paper/2402.01787/) (2024)
- [Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment](https://mlsanity.com/paper/2507.19002/) (2025)
- [A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2502.14896/) (2025)
- [A Survey on Responsible Generative AI: What to Generate and What Not](https://mlsanity.com/paper/2404.05783/) (2024)
- [OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models](https://mlsanity.com/paper/2505.21347/) (2025)

## Built on by (most cited first, 2 of 2)

- [JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization](https://mlsanity.com/paper/2603.21208/) (2026)
- [R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement](https://mlsanity.com/paper/2607.07318/) (2026)

## Abstract (arXiv)

With the rapid advancement of text-to-image (T2I) models, ensuring their safety has become increasingly critical. Existing safety approaches can be categorized into training-time and inference-time methods. While inference-time methods are widely adopted due to their cost-effectiveness, they often suffer from limitations such as over-refusal and imbalance between safety and utility. To address these challenges, we propose a multi-round safety editing framework that functions as a model-agnostic, plug-and-play module, enabling efficient safety alignment for any text-to-image model. Central to this framework is MR-SafeEdit, a multi-round image-text interleaved dataset specifically constructed for safety editing in text-to-image generation. We introduce a post-hoc safety editing paradigm that mirrors the human cognitive process of identifying and refining unsafe content. To instantiate this paradigm, we develop SafeEditor, a unified MLLM capable of multi-round safety editing on generated images. Experimental results show that SafeEditor surpasses prior safety approaches by reducing over-refusal while achieving a more favorable safety-utility balance.