arXiv:2607.17305cs.AIcs.CR2026-07

用强化学习动态调度链下数据审计,兼顾成本、漏检率和延迟。

Learning-Driven Adaptive Audit Scheduling: A Sequential Decision Approach to Off-Chain Data Integrity

论文配图:Learning-Driven Adaptive Audit Scheduling: A Sequential Decision Approach to Off-Chain Data Integrity
图 1 · 摘自论文原文
  • 将审计建模为带约束的马尔可夫决策过程,用GRU网络跟踪节点状态信念。
  • 漏检率仅7.5%,气体消耗比固定高频审计低83%,检测延迟适中。
  • 适合区块链系统中需高效保障数据完整性的工程场景。

我们将链下数据的密码学审计建模为部分可观测条件下的受限马尔可夫决策过程(CMDP):存储节点的隐藏类型与污染状态使其成为部分可观测马尔可夫决策过程(POMDP),而漏检率上限ρ构成显式安全约束。我们提出DRQN-CMDP,一种基于深度循环Q网络的算法,其GRU层用于维护对潜在节点类型的信念,并结合拉格朗日对偶上升法自动调整漏检惩罚系数λ。采用无配对同态消息认证码(homomorphic-MAC)实现链上验证开销恒定(O(1))。在13种方法——包括四种DQN变体、PPO、A2C、PPO-Lagrangian、一种有状态贝叶斯启发式、三种固定规则基线及一个知情启发式——中,DRQN-CMDP实现了最优平衡:气体消耗比固定高频审计降低83%,漏检率仅为7.5%,检测延迟适中,三者协同表现无其他方法能匹敌。

原文摘要 · Abstract (English)

We model cryptographic auditing of off-chain data as a Constrained MDP (CMDP) under partial observability: the storage node's hidden type and corruption state make the problem a POMDP, while a miss-rate ceiling rho imposes an explicit security constraint. We propose DRQN-CMDP, a Deep Recurrent Q-Network whose GRU layer maintains a belief over the latent node type, paired with Lagrangian dual ascent that adapts the miss-rate penalty lambda automatically. A pairing-free homomorphic-MAC primitive supplies O(1) on-chain verification cost. Across 13 methods--four DQN variants, PPO, A2C, PPO-Lagrangian, a stateful Bayesian heuristic, three fixed-rule baselines, and an oracle-informed heuristic--DRQN-CMDP achieves a favourable balance: 83% lower gas than fixed high-frequency auditing, single-digit miss rate (7.5%), and moderate detection latency--a combination no other method matches across all three objectives simultaneously.

强化学习区块链数据完整性动态审计

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。