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

2026-07-19

AI Summary

This work addresses the challenge of efficient and secure auditing for off-chain data storage nodes in partially observable environments by formulating it as a constrained partially observable Markov decision process (CMDP). The authors propose the DRQN-CMDP algorithm, which integrates a deep recurrent Q-network with Lagrangian dual ascent to dynamically optimize auditing policies. To minimize on-chain verification overhead, they introduce a pairing-free homomorphic message authentication code (MAC), achieving constant verification cost on-chain. Under a stringent false detection rate constraint of 7.5%, the proposed method reduces Gas consumption by 83% compared to fixed high-frequency auditing, while maintaining controllable detection latency. Comprehensive experiments demonstrate that this approach significantly outperforms thirteen baseline methods in overall performance.

Abstract

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.

Problem

• off-chain data integrity
• adaptive audit scheduling
• constrained MDP
• partial observability
• miss-rate constraint

Innovation

• DRQN-CMDP
• Constrained POMDP
• homomorphic-MAC
• adaptive audit scheduling
• off-chain data integrity