提出可抵抗模型蒸馏的架构理论，让能力与稳定性绑定，防止能力被低成本复制。
A Public Theory of Distillation Resistance via Constraint-Coupled Reasoning Architectures
- 通过约束耦合机制，将模型能力与内部稳定性关联，阻碍知识蒸馏
- 定义四要素框架：状态转移负担、路径负载累积、动态可行区域、能力-稳定耦合条件
- 理论框架公开透明，适合研究模型治理与对齐的学者参考
知识蒸馏、模型提取和行为迁移已成为前沿人工智能的核心关切。主要风险不仅是代码复制，更在于有用能力可能以远低于原始治理结构成本的方式被转移。本文提出一个公开、保密安全的理论框架，从架构层面降低这种不对称性。核心观点是：当高级能力与随时间演变的内部稳定性约束相耦合时，蒸馏作为捷径的价值会下降。为此，论文引入包含四个要素的约束耦合推理框架：有限转移负担、路径负载累积、动态演化可行区域，以及能力-稳定性耦合条件。该论文刻意保持公开安全，省略专有实现细节、训练方法、阈值设定、隐藏状态监控、部署流程及机密系统设计。因此贡献为理论性而非操作性，提供可验证的架构假说、明确威胁模型，以及未来关于蒸馏抗性、对齐与模型治理的可实验假设。
原文摘要 · Abstract (English)
Knowledge distillation, model extraction, and behavior transfer have become central concerns in frontier AI. The main risk is not merely copying, but the possibility that useful capability can be transferred more cheaply than the governance structure that originally accompanied it. This paper presents a public, trade-secret-safe theoretical framework for reducing that asymmetry at the architectural level. The core claim is that distillation becomes less valuable as a shortcut when high-level capability is coupled to internal stability constraints that shape state transitions over time. To formalize this idea, the paper introduces a constraint-coupled reasoning framework with four elements: bounded transition burden, path-load accumulation, dynamically evolving feasible regions, and a capability-stability coupling condition. The paper is intentionally public-safe: it omits proprietary implementation details, training recipes, thresholds, hidden-state instrumentation, deployment procedures, and confidential system design choices. The contribution is therefore theoretical rather than operational. It offers a falsifiable architectural thesis, a clear threat model, and a set of experimentally testable hypotheses for future work on distillation resistance, alignment, and model governance.
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。