← 研踪 PaperTrailarXiv:2611.08042 · v1
Secure Formal Raising: Protecting the Development of AI through Executable Properties
首次提交 2026-11-05 21:59
版本更新 2026-11-05 21:59
雷达观测 2026-11-06 12:09
摘要
Model raising revisits Turing's developmental view of machine intelligence. Formal Raising (FR) has recently been proposed to complement this view with explicit behavioral properties. This paper extends that proposal to the security of the raising environment. Secure Formal Raising (SFR) models policy integrity, authorization, and confidential data flow using four-valued evidence that preserves unknown and inconsistent assessments. We prove six security invariants and show that they force admission to accept only confirmed evidence. A plain-C reference implementation satisfies the invariants in a bounded exhaustive exploration, which also exposes a confused-deputy gap for tool calls that a provenance requirement closes.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-05 21:59 · 最新观测版本
Secure Formal Raising: Protecting the Development of AI through Executable Properties
Model raising revisits Turing's developmental view of machine intelligence. Formal Raising (FR) has recently been proposed to complement this view with explicit behavioral properties. This paper extends that proposal to the security of the raising environment. Secure Formal Raising (SFR) models policy integrity, authorization, and confidential data flow using four-valued evidence that preserves unknown and inconsistent assessments. We prove six security invariants and show that they force admission to accept only confirmed evidence. A plain-C reference implementation satisfies the invariants in a bounded exhaustive exploration, which also exposes a confused-deputy gap for tool calls that a provenance requirement closes.
查看此版本解读 →查看此版本原文 ↗