揭示大模型跨阶段信任漏洞，提出零信任防御框架
Unvalidated Trust: Cross-Stage Vulnerabilities in Large Language Model Architectures
- 梳理41种商用大模型的跨阶段风险模式
- 发现输入可引发非中性响应与隐式状态改变
- 推荐零信任设计，适合系统安全研究者参考
随着大语言模型越来越多地集成到自动化多阶段流程中，各处理阶段间因缺乏验证而产生的信任漏洞成为实际问题。本文构建了一个以机制为中心的41种常见风险模式分类体系。分析表明，输入常被非中性解读，即使无明确指令也可能触发特定实现行为或意外状态变化。我们指出这些现象构成架构层面的失效模式，仅靠字符串级过滤不足以应对。为缓解此类跨阶段漏洞，建议采用零信任架构原则，包括溯源验证、上下文封印和计划重校验，并提出“Countermind”作为实现这些防御的概念蓝图。
原文摘要 · Abstract (English)
As Large Language Models (LLMs) are increasingly integrated into automated, multi-stage pipelines, risk patterns that arise from unvalidated trust between processing stages become a practical concern. This paper presents a mechanism-centered taxonomy of 41 recurring risk patterns in commercial LLMs. The analysis shows that inputs are often interpreted non-neutrally and can trigger implementation-shaped responses or unintended state changes even without explicit commands. We argue that these behaviors constitute architectural failure modes and that string-level filtering alone is insufficient. To mitigate such cross-stage vulnerabilities, we recommend zero-trust architectural principles, including provenance enforcement, context sealing, and plan revalidation, and we introduce "Countermind" as a conceptual blueprint for implementing these defenses.
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。