# Direct Unlearning Optimization for Robust and Safe Text-to-Image Models

arXiv: https://arxiv.org/abs/2407.21035 · HTML: https://mlsanity.com/paper/2407.21035/

## Key facts

- Cited by 50 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 54 of its 67 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## 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, 30 of 54)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Unified Concept Editing in Diffusion Models](https://mlsanity.com/paper/2308.14761/) (2023)
- [Understanding Diffusion Models: A Unified Perspective](https://mlsanity.com/paper/2208.11970/) (2022)
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023)
- [MACE: Mass Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2403.06135/) (2024)

## Built on by (most cited first, 30 of 50)

- [SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation](https://mlsanity.com/paper/2410.12761/) (2024)
- [Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts](https://mlsanity.com/paper/2504.12782/) (2025)
- [Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts](https://mlsanity.com/paper/2410.12777/) (2024)
- [Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey](https://mlsanity.com/paper/2411.09259/) (2024)
- [Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models](https://mlsanity.com/paper/2408.00523/) (2024)
- [CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models](https://mlsanity.com/paper/2505.12677/) (2025)
- [PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models](https://mlsanity.com/paper/2501.03544/) (2025)
- [Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances](https://mlsanity.com/paper/2508.10316/) (2025)
- [Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression](https://mlsanity.com/paper/2505.19398/) (2025)
- [Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning](https://mlsanity.com/paper/2507.07139/) (2025)
- [Erased but Not Forgotten: How Backdoors Compromise Concept Erasure](https://mlsanity.com/paper/2504.21072/) (2025)
- [EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment](https://mlsanity.com/paper/2511.00804/) (2025)
- [CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary](https://mlsanity.com/paper/2501.15562/) (2025)
- [Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling](https://mlsanity.com/paper/2505.21074/) (2025)
- [SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2509.05625/) (2025)
- [Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise Optimization](https://mlsanity.com/paper/2412.03876/) (2024)
- [Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations](https://mlsanity.com/paper/2501.19066/) (2025)
- [The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models](https://mlsanity.com/paper/2507.18725/) (2025)
- [Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2510.24012/) (2025)
- [Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control](https://mlsanity.com/paper/2503.18324/) (2025)
- [Concept Unlearning by Modeling Key Steps of Diffusion Process](https://mlsanity.com/paper/2507.06526/) (2025)
- [Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generation](https://mlsanity.com/paper/2511.18684/) (2025)
- [Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2603.25994/) (2026)
- [Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models](https://mlsanity.com/paper/2509.22723/) (2025)
- [CGCE: Classifier-Guided Concept Erasure in Generative Models](https://mlsanity.com/paper/2511.05865/) (2025)
- [Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping](https://mlsanity.com/paper/2605.10937/) (2026)
- [ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models](https://mlsanity.com/paper/2507.21985/) (2025)
- [VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation](https://mlsanity.com/paper/2509.16986/) (2025)
- [Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning](https://mlsanity.com/paper/2510.17917/) (2025)
- [SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers](https://mlsanity.com/paper/2604.01826/) (2026)

## Abstract (arXiv)

Recent advancements in text-to-image (T2I) models have unlocked a wide range of applications but also present significant risks, particularly in their potential to generate unsafe content. To mitigate this issue, researchers have developed unlearning techniques to remove the model's ability to generate potentially harmful content. However, these methods are easily bypassed by adversarial attacks, making them unreliable for ensuring the safety of generated images. In this paper, we propose Direct Unlearning Optimization (DUO), a novel framework for removing Not Safe For Work (NSFW) content from T2I models while preserving their performance on unrelated topics. DUO employs a preference optimization approach using curated paired image data, ensuring that the model learns to remove unsafe visual concepts while retaining unrelated features. Furthermore, we introduce an output-preserving regularization term to maintain the model's generative capabilities on safe content. Extensive experiments demonstrate that DUO can robustly defend against various state-of-the-art red teaming methods without significant performance degradation on unrelated topics, as measured by FID and CLIP scores. Our work contributes to the development of safer and more reliable T2I models, paving the way for their responsible deployment in both closed-source and open-source scenarios.