mlsanityData to 14 Oct 2026

Ethical-Lens: Curbing Malicious Usages of Open-Source Text-to-Image Models

arXiv 2404.12104 ↗First posted 18 Apr 2024cs.CV cs.CL cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

The burgeoning landscape of text-to-image models, exemplified by innovations such as Midjourney and DALLE 3, has revolutionized content creation across diverse sectors. However, these advancements bring forth critical ethical concerns, particularly with the misuse of open-source models to generate content that violates societal norms. Addressing this, we introduce Ethical-Lens, a framework designed to facilitate the value-aligned usage of text-to-image tools without necessitating internal model revision. Ethical-Lens ensures value alignment in text-to-image models across toxicity and bias dimensions by refining user commands and rectifying model outputs. Systematic evaluation metrics, combining GPT4-V, HEIM, and FairFace scores, assess alignment capability. Our experiments reveal that Ethical-Lens enhances alignment capabilities to levels comparable with or superior to commercial models like DALLE 3, ensuring user-generated content adheres to ethical standards while maintaining image quality. This study indicates the potential of Ethical-Lens to ensure the sustainable development of open-source text-to-image tools and their beneficial integration into society. Our code is available at https://github.com/yuzhu-cai/Ethical-Lens.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 35 of its 62 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

35 of 62 references.

References · 35

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  10. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  11. 2014Going Deeper with Convolutionscited by 4,241
  12. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
23 more
  1. 2023Qwen Technical Reportcited by 3,344
  2. 2016Improved Techniques for Training GANscited by 2,970
  3. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  4. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  5. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 790
  6. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 513
  7. 2021Image Segmentation Using Text and Image Promptscited by 512
  8. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  9. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  10. 2022DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Modelscited by 230
  11. 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 213
  12. 2023Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Modelscited by 175
  13. 2023Holistic Evaluation of Text-To-Image Modelscited by 160
  14. 2023Fair Diffusion: Instructing Text-to-Image Generation Models on Fairnesscited by 151
  15. 2023Social Biases through the Text-to-Image Generation Lenscited by 127
  16. 2022Retrieval-Augmented Multimodal Language Modelingcited by 125
  17. 2022ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model with Knowledge-Enhanced Mixture-of-Denoising-Expertscited by 112
  18. 2023Finetuning Text-to-Image Diffusion Models for Fairnesscited by 92
  19. 2023On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Drivingcited by 80
  20. 2024CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusioncited by 72
  21. 2023The Bias Amplification Paradox in Text-to-Image Generationcited by 70
  22. 2023Adaptive Nonlinear Latent Transformation for Conditional Face Editingcited by 9
  23. 2023State-of-the-Art in Nudity Classification: A Comparative Analysiscited by 3

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generationcited by 133
  2. 2025Safety at Scale: A Comprehensive Survey of Large Model and Agent Safetycited by 67
  3. 2025CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Modelscited by 27
  4. 2025Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generationcited by 4