← 研踪 PaperTrailCVF · CVPR 2026:cvf:2ff2a14d51e15cb0e57a0ae6e3569f68 · 记录 #1
GenBreak: Red Teaming Text-to-Image Generation Using Large Language Models
来源日期（仅到年份） 2026
来源记录日期 2026
雷达观测 2026-11-05 02:15
摘要
Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation systems, underlying vulnerabilities can still be exploited by adversaries. Recent research on red-teaming and adversarial attacks against T2I models faces a critical limitation: existing methods struggle to balance prompt stealthiness with image toxicity. Some studies successfully generate highly toxic images but use adversarial prompts that are easily detected by safety filters, while others focus on bypassing safety mechanisms but fail to produce genuinely harmful outputs, neglecting the discovery of truly high-risk prompts. Consequently, there remains a lack of reliable tools for evaluating the safety of defended T2I models. To address this gap, we propose GenBreak, a framework that fine-tunes a red-team large language model (LLM) to systematically explore underlying vulnerabilities in T2I generators. Our approach combines supervised fine-tuning on curated datasets with reinforcement learning via interaction with a surrogate T2I model. By integrating multiple reward signals, we guide the LLM to craft adversarial prompts that enhance both evasion capability and image toxicity, while maintaining semantic coherence and diversity. These prompts demonstrate strong effectiveness in black-box attacks against commercial T2I generators, revealing practical safety weaknesses. Code is available at https://github.com/wangdandan567/RT-diffuser.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
GenBreak: Red Teaming Text-to-Image Generation Using Large Language Models
Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation systems, underlying vulnerabilities can still be exploited by adversaries. Recent research on red-teaming and adversarial attacks against T2I models faces a critical limitation: existing methods struggle to balance prompt stealthiness with image toxicity. Some studies successfully generate highly toxic images but use adversarial prompts that are easily detected by safety filters, while others focus on bypassing safety mechanisms but fail to produce genuinely harmful outputs, neglecting the discovery of truly high-risk prompts. Consequently, there remains a lack of reliable tools for evaluating the safety of defended T2I models. To address this gap, we propose GenBreak, a framework that fine-tunes a red-team large language model (LLM) to systematically explore underlying vulnerabilities in T2I generators. Our approach combines supervised fine-tuning on curated datasets with reinforcement learning via interaction with a surrogate T2I model. By integrating multiple reward signals, we guide the LLM to craft adversarial prompts that enhance both evasion capability and image toxicity, while maintaining semantic coherence and diversity. These prompts demonstrate strong effectiveness in black-box attacks against commercial T2I generators, revealing practical safety weaknesses. Code is available at https://github.com/wangdandan567/RT-diffuser.
查看此版本解读 →查看此版本原文 ↗