paper-with-me

홈 › Papers

Universal Prompt Optimizer for Safe Text-to-Image Generation

2024-02-16 · Zongyu Wu, Hongcheng Gao, Yueze Wang, Xiang Zhang, Suhang Wang

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.

📄 PDF Abstract BibTeX arXiv:2402.10882

Code (1)

wu-zongyu/posi 공식 구현 pytorch

Tasks

BlockingImage GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…

Similar Papers 제목 키워드 기반

Universally Unfiltered and Unseen:Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards

2025-07-30 · Song Yan, Hui Wei, Jinlong Fei, Guoliang Yang 외 arxiv

Various (text) prompt filters and (image) safety checkers have been implemented to mitigate the misuse of Text-to-Image (T2I) models in creating Not-Safe-For-Work (NSFW) content. In order to expose potential security vul…

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models

2025-09-16 · Yunhan Zhao, Xiang Zheng, Xingjun Ma arxiv

Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, their effectiveness and efficiency can still…

PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models

2025-01-07 · Lingzhi Yuan, Xiaojun Jia, Yihao Huang, Wei Dong 외

Text-to-image (T2I) models have been shown to be vulnerable to misuse, particularly in generating not-safe-for-work (NSFW) content, raising serious ethical concerns. In this work, we present PromptGuard, a novel content …

Image GenerationSafety Alignment

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation

2025-08-02 · Zonglei Jing, Xiao Yang, Xiaoqian Li, Siyuan Liang 외 arxiv

Text-to-image (T2I) models have demonstrated remarkable generative capabilities but remain vulnerable to producing not-safe-for-work (NSFW) content, such as violent or explicit imagery. While recent moderation efforts ha…

Text-to-Image Generation

Universal Adversarial Attack on Aligned Multimodal LLMs

2025-02-11 · Temurbek Rahmatullaev, Polina Druzhinina, Matvey Mikhalchuk, Andrey Kuznetsov 외

We propose a universal adversarial attack on multimodal Large Language Models (LLMs) that leverages a single optimized image to override alignment safeguards across diverse queries and even multiple models. By backpropag…

Adversarial Attack