科研速览 · Science Skim继续刷下去 · Keep skimming →
◇ arXiv2026-09-07· cs.CR

Compute-Bounded Security Assurance - Coverage, Verification, and Response under Resource Constraints

Jithin VG, Ditto PS

原始摘要(英文原文)· Original abstract
Additional inference compute can increase the number of correctly resolved security-assurance tasks, but repeated success, unique coverage, accepted evidence, and operational protection are different quantities. We develop a resource-constrained framework that separates them. For repeated conditionally independent attempts with latent success probability $Θ$, coverage is $C_n = 1 - E[(1-Θ)^n]$, and its limiting value is $1 - P(Θ= 0)$. Positive pairwise outcome correlation does not by itself imply a ceiling below one: we construct two models with the same mean success and pairwise correlation but different limiting coverage. We distinguish this result from the effective sample size used to estimate a mean, and show why finite-budget observations cannot generally identify an asymptotic support ceiling. We then connect coverage to fallible evidence checking, proper scoring of factual grounding, complete resource accounting, service capacity, and a response model that includes mitigation delay. A conceptual defensive architecture separates evidence analysis, adjudication, and operational authority. An evaluation protocol specifies held-out tasks, paired comparisons, negative cases, and uncertainty reporting. The contribution is a consistent theoretical synthesis and a set of counterexamples to invalid extrapolations, rather than an empirical scaling law. All numerical illustrations are analytic; no model-parity result, hardware benchmark, or general attacker-defender equilibrium is claimed.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

Compute-Bounded Security Assurance - Coverage, Verification, and Response under Resource Constraints — 科研速览 Science Skim