Bitcoin's design promises resilience through decentralization, yet the physical infrastructure supporting the network creates hidden dependencies. We present the first longitudinal study of Bitcoin's resilience to submarine cable failures, using 11 years of P2P network data (2014--2025) and 68 verified cable fault events. Applying a Buldyrev-style cascade model at country level, we find that Bitcoin's clearnet (non-TOR) critical failure threshold $p_c \approx 0.72$--$0.92$ for random failures, meaning the vast majority of inter-country cables must fail before significant node disconnection. Targeted attacks are an order of magnitude more effective ($p_c = 0.05$--$0.20$). To address the majority of nodes now using TOR with unobservable locations, we develop a 4-layer multiplex model incorporating TOR relay infrastructure. Because relay bandwidth concentrates in well-connected European countries, TOR adoption increases resilience under current relay geography ($Δp_c \approx +0.02$--$+0.10$) rather than introducing hidden fragility. Empirical validation confirms weak physical-layer coupling: 87% of historical cable faults caused less than 5% node impact. We contribute: (1) a multiplex percolation framework for overlay-underlay coupling, including a 4-layer TOR relay model; (2) the first empirical measurement of Bitcoin's physical-layer resilience over a decade; and (3) evidence that TOR adoption amplifies resilience, with distributional bounds quantifying uncertainty under partial observability.

翻译：比特币的设计通过去中心化承诺了韧性，但支撑网络的物理基础设施却造成了隐藏的依赖性。我们利用11年的P2P网络数据（2014-2025年）和68次已验证的海底光缆故障事件，首次对海底光缆故障下比特币的韧性进行了纵向研究。在国家层面应用Buldyrev式级联模型，我们发现比特币明网（非TOR）在随机故障下的临界失效阈值$p_c \approx 0.72$--$0.92$，这意味着绝大部分跨国光缆必须失效才会导致显著的节点断开。针对性攻击的有效性高出一个数量级（$p_c = 0.05$--$0.20$）。针对目前大多数节点使用TOR导致位置不可观测的问题，我们开发了一个包含TOR中继基础设施的四层复用模型。由于中继带宽集中在连接良好的欧洲国家，在当前中继地理分布下，TOR的采用反而增强了韧性（$Δp_c \approx +0.02$--$+0.10$），而非引入隐藏的脆弱性。实证验证证实了物理层耦合较弱：87%的历史光缆故障造成的节点影响小于5%。我们的贡献在于：（1）一个用于覆盖层-底层耦合的复用渗流框架，包括一个四层TOR中继模型；（2）首次对十余年来比特币物理层韧性的实证测量；（3）证据表明TOR的采用增强了韧性，并提供了在部分可观测性下量化不确定性的分布界限。