Buster:在文本编码器中植入语义后门以缓解NSFW内容生成
Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation
AI总结:
针对现有NSFW内容生成防御方法的不足,研究提出Buster框架,通过在文本编码器注入语义后门、结合基于能量的对抗数据增强,高效实现高移除率的NSFW内容抑制且保留良性图像质量。
摘要:
数字时代深度学习模型的兴起引发了人们对非工作安全(Not-Safe-for-Work,NSFW)内容生成的大量担忧。现有防御方法主要包括模型微调和事后内容审核。然而,这些方法在消除有害内容方面大多缺乏可扩展性,会降低良性图像生成的质量,或产生高昂的推理成本。为应对这些挑战,我们提出了一个名为Buster的创新框架,该框架通过在文本编码器中注入后门来阻止NSFW内容生成。Buster利用深度语义信息而非显式提示作为触发器,将NSFW提示重定向到目标良性提示。此外,Buster采用基于能量的训练数据生成方法,通过朗之万动力学(Langevin dynamics)实现对抗性知识增强,从而确保有害概念定义的鲁棒性。该方法在缓解NSFW内容方面展现出卓越的韧性和可扩展性。值得注意的是,Buster仅需五分钟即可微调文本到图像(Text-to-Image)模型的文本编码器,体现了其高效性。我们的大量实验表明,Buster优于9种最先进的基线方法,实现了至少91.2%的优异NSFW内容移除率,同时保留了无害图像的质量。
英文摘要:
The rise of deep learning models in the digital era has raised substantial concerns regarding the generation of Not-Safe-for-Work (NSFW) content. Existing defense methods primarily involve model fine-tuning and post-hoc content moderation. Nevertheless, these approaches largely lack scalability in eliminating harmful content, degrade the quality of benign image generation, or incur high inference costs. To address these challenges, we propose an innovative framework named \textit{Buster}, which injects backdoors into the text encoder to prevent NSFW content generation. Buster leverages deep semantic information rather than explicit prompts as triggers, redirecting NSFW prompts towards targeted benign prompts. Additionally, Buster employs energy-based training data generation through Langevin dynamics for adversarial knowledge augmentation, thereby ensuring robustness in harmful concept definition. This approach demonstrates exceptional resilience and scalability in mitigating NSFW content. Particularly, Buster fine-tunes the text encoder of Text-to-Image models within merely five minutes, showcasing its efficiency. Our extensive experiments denote that Buster outperforms nine state-of-the-art baselines, achieving a superior NSFW content removal rate of at least 91.2\% while preserving the quality of harmless images.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。