Secure Formal Raising: Protecting the Development of AI through Executable Properties
· arxiv.org · popularity 7/100 · 0 similar stories today
Read the original at arxiv.org →
Summary
arXiv:2611.08042v1 Announce Type: new Abstract: 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.
Found in: ArXiv CS.AI. Rating basis: single outlet; outlet tier 2 (unlisted); 1 feeds; feed position 48.