发表机构
AIDECISIONS（艾迪赛斯公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出了一个覆盖5条EVM链、含8.35亿地址的多链交易图合规性筛查系统，可实现无标签迁移，在提前标记制裁地址等任务上表现优于基线，同时具备高效服务能力，也发现了模型的合成行为盲区。
AI 中文摘要
区块链地址的合规性筛查在实践中是对照制裁登记库加聚类启发式方法进行的；该方法在未标记地址以及完全无标签覆盖的链上失效。我们描述了一个已部署的系统，该系统通过地址在多链交易图中的位置而非其是否存在于列表中来对地址评分。其基础是一个包含835,330,427个地址和15,826,261,934条边的单图，覆盖5条EVM链；一个带每条链归一化的共享归纳编码器为两个评分头提供输入。决策阈值是全人口评分分布的精确分位数，按每条链段扫描，因此警报量可预先知晓。我们报告：无标签迁移：在两条链上训练的评分头，在10^-3的人口警报率下，对Base、Arbitrum和Gnosis上保留的正样本召回率为0.8598/0.8182/0.9967，且评分头训练中无目标链标签；对68个外部登记事件的静态提前时间重放：在0.1%预算下标记了68个中的40个（58.8%），是事件级随机标记基线的152倍，在公开指定前，首次链上出现的中位数时间为以太坊528.8天/波场647.8天；服务路径的评分与离线制品逐位相同，端到端p50为151毫秒，由2,882个地址漂移面板控制；以及一个包含8个循环强化学习原型的对抗工具，其通过了8项标准的退化审计，且在与检测器无关的快照上，揭示了已部署评分头对合成行为的可测量盲区。
英文摘要
Compliance screening of blockchain addresses is, in practice, a lookup against sanctions registries plus clustering heuristics; it fails on unlabelled addresses and on chains with no label coverage at all. We describe a deployed system that scores an address by its position in a multi-chain transaction graph rather than by its presence in a list. The substrate is a single graph of 835,330,427 addresses and 15,826,261,934 edges across five EVM chains; a shared inductive encoder with per-chain normalisation feeds two scoring heads. Decision thresholds are exact quantiles of the score distribution over the full population, scanned per chain segment, so the alert volume is known in advance. We report: label-free transfer: heads trained on two chains recall 0.8598 / 0.8182 / 0.9967 of held-out positives on Base, Arbitrum and Gnosis at a $10^{-3}$ population alert rate, with no target-chain labels in head training; a static lead-time replay over 68 external registry events: 40 of 68 (58.8%) flagged at the 0.1% budget, $\times$152 over an event-level random-flagging baseline, with first on-chain appearance a median of 528.8 days (Ethereum) / 647.8 days (Tron) before public designation; a serving path whose score is bit-identical to the offline artefact at end-to-end p50 151 ms, gated by a 2,882-address drift panel; and an adversarial harness of eight recurrent reinforcement-learned archetypes that passes an 8-criterion degeneracy audit and, on a detector-independent snapshot, exposes a measured blind spot of the deployed heads against synthesised behaviour.
Comments25 pages, 9 tables. Code and evaluation harness: https://github.com/ai-decisions
