Pith. sign in

REVIEW 7 cited by

Universal Prompt Optimizer for Safe Text-to-Image Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.10882 v6 pith:RWRJIAWK submitted 2024-02-16 cs.CV cs.CL

Zongyu Wu , Hongcheng Gao , Yueze Wang , Xiang Zhang , Suhang Wang This is my paper · ORCID
classification cs.CVcs.CL
keywords promptimagesoptimizermodelsalignmentfirstgeneratinggeneration
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Text-to-Image (T2I) models have shown great performance in generating images based on textual prompts. However, these models are vulnerable to unsafe input to generate unsafe content like sexual, harassment and illegal-activity images. Existing studies based on image checker, model fine-tuning and embedding blocking are impractical in real-world applications. Hence, we propose the first universal prompt optimizer for safe T2I (POSI) generation in black-box scenario. We first construct a dataset consisting of toxic-clean prompt pairs by GPT-3.5 Turbo. To guide the optimizer to have the ability of converting toxic prompt to clean prompt while preserving semantic information, we design a novel reward function measuring toxicity and text alignment of generated images and train the optimizer through Proximal Policy Optimization. Experiments show that our approach can effectively reduce the likelihood of various T2I models in generating inappropriate images, with no significant impact on text alignment. It is also flexible to be combined with methods to achieve better performance. Our code is available at https://github.com/wu-zongyu/POSI.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding

    cs.CR 2024-11 conditional novelty 7.0 of 10

    Embedding Sanitizer removes inappropriate concepts directly from text prompt embeddings with per-token scores, claiming state-of-the-art robustness against adversarial prompts.

  2. SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    SafeCFG adapts classifier-free guidance with a learned feature controller so that clean prompts generate normally while harmful prompts are pushed away from unsafe content.

  3. Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Prompt-A-Video refines text prompts for video diffusion models via evolutionary search and DPO alignment, improving generated video quality on Open-Sora and CogVideoX.

  4. Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization

    cs.CR 2024-12 conditional novelty 6.0 of 10

    Summarizing LLM-obfuscated text-to-image prompts before classification improves content-moderation F1 scores on the new ATTIP dataset.

  5. Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise Optimization

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Prompt-Noise Optimization jointly tunes the prompt embedding and diffusion noise at inference time to suppress unsafe images while keeping outputs close to the prompt.

  6. Text to Image Generation and Editing: A Survey

    cs.CV 2025-05 conditional novelty 3.0 of 10

    A broad survey of text-to-image generation and editing research from 2021 to 2024, organized by architecture and comparison tables.

  7. Text-to-Image Synthesis: A Decade Survey

    cs.CV 2024-11 conditional novelty 1.0 of 10

    A decade-spanning survey categorizes over 440 text-to-image papers by architecture, research problem, dataset, and evaluation metric.

Pith tools