mlsanityData to 7 Oct 2026

SP-Guard: Selective Prompt-adaptive Guidance for Safe Text-to-Image Generation

arXiv 2511.11014 ↗First posted 14 Nov 2025cs.CV cs.CYcited by 0

On the map: LLM safety and security → Vision-language and text-to-image safety

Abstract (arXiv)

While diffusion-based T2I models have achieved remarkable image generation quality, they also enable easy creation of harmful content, raising social concerns and highlighting the need for safer generation. Existing inference-time guiding methods lack both adaptivity--adjusting guidance strength based on the prompt--and selectivity--targeting only unsafe regions of the image. Our method, SP-Guard, addresses these limitations by estimating prompt harmfulness and applying a selective guidance mask to guide only unsafe areas. Experiments show that SP-Guard generates safer images than existing methods while minimizing unintended content alteration. Beyond improving safety, our findings highlight the importance of transparency and controllability in image generation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security. Builds on 33 of its 39 references that are in the map. First posted on arXiv 14 Nov 2025.

Builds on

33 of 39 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation16 Oct
  2. 2024ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning29 May
  3. 2024GuardT2I: Defending Text-to-Image Models from Adversarial Prompts3 Mar
  4. 2023To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now18 Oct
  5. 2023Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?16 Oct

Other references · 28

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2022Classifier-Free Diffusion Guidancecited by 5,717
  7. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  9. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  10. 2023Erasing Concepts from Diffusion Modelscited by 530
  11. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 501
  12. 2023Unified Concept Editing in Diffusion Modelscited by 377
16 more
  1. 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 326
  2. 2023MMA-Diffusion: MultiModal Attack on Diffusion Modelscited by 184
  3. 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Modelscited by 175
  4. 2023Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Modelscited by 171
  5. 2022Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?cited by 150
  6. 2023LEDITS++: Limitless Image Editing using Text-to-Image Modelscited by 147
  7. 2024Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Modelscited by 123
  8. 2023Evaluating the Social Impact of Generative AI Systems in Systems and Societycited by 91
  9. 2024Latent Guard: a Safety Framework for Text-to-image Generationcited by 68
  10. 2024UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Imagescited by 52
  11. 2024Towards Understanding the Working Mechanism of Text-to-Image Diffusion Modelcited by 48
  12. 2023NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Modelscited by 46
  13. 2023Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizationscited by 45
  14. 2024Universal Prompt Optimizer for Safe Text-to-Image Generationcited by 27
  15. 2023Clockwork Diffusion: Efficient Generation With Model-Step Distillationcited by 18
  16. 2024Safeguard Text-to-Image Diffusion Models with Human Feedback Inversioncited by 10

Built on by

Not cited yet.