PromptCARE：通过水印注入与验证进行提示词版权保护
PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification
AI总结：
提出首个提示词版权保护框架PromptCARE，通过定制的水印注入与验证方案克服现有技术局限，在多个基准和模型上验证了其有效、无害、鲁棒且隐蔽。
摘要：
在过去的几个月里，大型语言模型（LLMs）在普通公众用户中的普及度迅速上升，以人类水平的准确性和熟练度促进了各种下游任务。提示词在这一成功中发挥了关键作用，它通过简单地在查询文本前添加一系列token，将预训练的LLMs高效地适配到特定任务应用中。然而，设计和选择最优提示词既昂贵又要求苛刻，这催生了提示词即服务提供商，他们通过提供精心设计的提示词供授权使用来获利。随着提示词的日益普及及其在基于LLM的服务中的不可或缺的作用，迫切需要保护提示词的版权，防止未经授权的使用。在本文中，我们提出了PromptCARE，这是第一个通过水印注入和验证进行提示词版权保护的框架。提示词水印面临着独特的挑战，使得为模型和数据集版权验证开发的现有水印技术无效。PromptCARE通过提出专为提示词和自然语言处理（NLP）特性量身定制的水印注入和验证方案来克服这些障碍。在六个知名基准数据集上，使用三种流行的预训练LLM（BERT、RoBERTa和Facebook OPT-1.3b）进行了大量实验，证明了PromptCARE的有效性、无害性、鲁棒性和隐蔽性。
英文摘要：
Large language models (LLMs) have witnessed a meteoric rise in popularity among the general public users over the past few months, facilitating diverse downstream tasks with human-level accuracy and proficiency. Prompts play an essential role in this success, which efficiently adapt pre-trained LLMs to task-specific applications by simply prepending a sequence of tokens to the query texts. However, designing and selecting an optimal prompt can be both expensive and demanding, leading to the emergence of Prompt-as-a-Service providers who profit by providing well-designed prompts for authorized use. With the growing popularity of prompts and their indispensable role in LLM-based services, there is an urgent need to protect the copyright of prompts against unauthorized use. In this paper, we propose PromptCARE, the first framework for prompt copyright protection through watermark injection and verification. Prompt watermarking presents unique challenges that render existing watermarking techniques developed for model and dataset copyright verification ineffective. PromptCARE overcomes these hurdles by proposing watermark injection and verification schemes tailor-made for prompts and NLP characteristics. Extensive experiments on six well-known benchmark datasets, using three prevalent pre-trained LLMs (BERT, RoBERTa, and Facebook OPT-1.3b), demonstrate the effectiveness, harmlessness, robustness, and stealthiness of PromptCARE.
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。
