mlsanityData to 14 Oct 2026

UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers

arXiv 2405.11336 ↗First posted 18 May 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Text-to-Image (T2I) models have raised security concerns due to their potential to generate inappropriate or harmful images. In this paper, we propose UPAM, a novel framework that investigates the robustness of T2I models from the attack perspective. Unlike most existing attack methods that focus on deceiving textual defenses, UPAM aims to deceive both textual and visual defenses in T2I models. UPAM enables gradient-based optimization, offering greater effectiveness and efficiency than previous methods. Given that T2I models might not return results due to defense mechanisms, we introduce a Sphere-Probing Learning (SPL) scheme to support gradient optimization even when no results are returned. Additionally, we devise a Semantic-Enhancing Learning (SEL) scheme to finetune UPAM for generating target-aligned images. Our framework also ensures attack stealthiness. Extensive experiments demonstrate UPAM's effectiveness and efficiency.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 27 of its 46 references that are in the map. First posted on arXiv 18 May 2024.

Builds on

27 of 46 references.

References · 27

  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. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  9. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  10. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  11. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  12. 2019Adversarial Training for Free!cited by 643
15 more
  1. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 513
  2. 2020Label-Only Membership Inference Attackscited by 388
  3. 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 327
  4. 2017Stochastic Gradient Descent as Approximate Bayesian Inferencecited by 300
  5. 2022Red-Teaming the Stable Diffusion Safety Filtercited by 264
  6. 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
  7. 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
  8. 2023BlackVIP: Black-Box Visual Prompting for Robust Transfer Learningcited by 70
  9. 2022Backdoor Defense with Machine Unlearningcited by 65
  10. 2022Label-Only Model Inversion Attacks via Boundary Repulsioncited by 56
  11. 2021Hard to Forget: Poisoning Attacks on Certified Machine Unlearningcited by 52
  12. 2022Discovering the Hidden Vocabulary of DALLE-2cited by 43
  13. 2022Adversarial Attacks on Image Generation With Made-Up Wordscited by 32
  14. 2019The LogBarrier adversarial attack: making effective use of decision boundary informationcited by 7
  15. 2023Continual Adversarial Defensecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 5.

12 papers.

  1. 2024Perception-guided Jailbreak against Text-to-Image Modelscited by 40
  2. 2024Jailbreak Attacks and Defenses against Multimodal Generative Models: A Surveycited by 32
  3. 2025A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Modelscited by 9
  4. 2025Unified Prompt Attack Against Text-to-Image Generation Modelscited by 5
  5. 2026DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generationcited by 4
  6. 2024Antelope: Potent and Concealed Jailbreak Attack Strategycited by 3
  7. 2026SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generationcited by 3
  8. 2025External Data Extraction Attacks against Retrieval-Augmented Large Language Modelscited by 2
  9. 2025Security Risk of Misalignment between Text and Image in Multi-modal Modelcited by 0
  10. 2026Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Modelscited by 0
  11. 2026The Safeguard Worked. Is the LLM System Safer?cited by 0
  12. 2026Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generationcited by 0