这篇论文提出一个聪明的防御思路，叫 Knowledge Trap，用蜜罐知识图消耗攻击者的查询预算，不影响正常用户，效果不错。
Knowledge Trap 是一种针对 LLM 模型提取攻击的防御方法，通过构建 Honeypot Knowledge Graph (HKG) 和面包屑引导探索，将攻击者的查询预算重定向到低迁移性的知识上。在医疗和金融领域的实验中，Knowledge Trap 使攻击者获得的代理模型一致性 (Agreement) 平均降低 6.2%，同时不影响合法用户的准确率。相比现有防御方法，Knowledge Trap 不会降低正常用户的体验。该研究表明，防御知识空间遍历是缓解 LLM 提取攻击的一个实用方向。
Let Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypot
Large language models deployed as commercial APIs are vulnerable to model extraction attacks, while existing defenses either act too late or degrade utility for legitimate users. We propose \textbf{Knowledge Trap}, a defense that redirects extraction attacks toward low-transferability knowledge through a \emph{Honeypot Knowledge Graph} (HKG) and breadcrumb-guided exploration. Instead of blocking queries or perturbing outputs, Knowledge Trap consumes the attacker's limited query budget on knowledge with negligible downstream utility while preserving benign-user performance. Experiments in medical and financial domains show that Knowledge Trap reduces surrogate Agreement by 6.2\% on average without degrading legitimate-user accuracy, outperforming existing defenses that impose measurable user impact. These results suggest that defending knowledge-space traversal is a practical direction for mitigating LLM extraction attacks.