用代码符号锚定语义，让提示词只在指定大模型上运行。
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
- 通过代码符号和模型反馈注入噪声，生成仅适配目标模型的混淆提示。
- 跨模型可移植性降低90%以上，且保持原任务性能不下降。
- 适合需保护提示词知识产权的AI代理开发者使用。
LLM智能体依赖提示词实现特定任务能力，这些提示词是重要知识产权。但在不可信部署中，攻击者可复制提示词并用于其他私有模型，造成经济损失。现有方法无法同时满足主动性、运行时保护、易用性和非可移植性需求。本文提出PragLocker，通过代码符号锚定语义，并利用目标模型反馈注入噪声，生成仅在目标LLM上有效的功能保持型混淆提示。在多个智能体系统、数据集和基础模型上的实验表明，PragLocker显著降低跨模型可移植性，维持目标性能，并对自适应攻击者具备鲁棒性。
原文摘要 · Abstract (English)
LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property. However, in untrusted deployments, adversaries can copy and reuse these prompts with other proprietary LLMs, causing economic losses. To protect these prompts, we identify four key challenges: proactivity, runtime protection, usability, and non-portability that existing approaches fail to address. We present PragLocker, a prompt protection scheme that satisfies these requirements. PragLocker constructs function-preserving obfuscated prompts by anchoring semantics with code symbols and then using target-model feedback to inject noise, yielding prompts that only work on the target LLM. Experiments across multiple agent systems, datasets, and foundation LLMs show that PragLocker substantially reduces cross-LLM portability, maintains target performance, and remains robust against adaptive attackers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。