When Routes Run Out: Adversarial Co-Learning and Explainable Robustness in Quantum Repeater Networks

2026-07-10

AI Summary

This work addresses the robust routing problem in quantum repeater networks under path exhaustion scenarios against adversarial attacks by proposing an adversarial multi-armed bandit framework. In this setting, Alice selects routes based on the E91 protocol, while Eve executes edge-interception or relay-memory-degradation attacks; outcomes are determined by violations of the CHSH inequality. Leveraging data generated via the SeQUeNCe platform, the approach integrates minimax strategy approximation with adversarial cooperative reinforcement learning and innovatively incorporates decision trees and language model prompt engineering to achieve, for the first time, interpretable and transparent analysis of learned strategies. The resulting policies exhibit strong alignment with full-matrix minimax benchmarks (Pearson r = 0.99), confirm zero retention for bottleneck topology families, and adhere to the 1−1/N coverage principle for non-bottleneck families. The complete workflow is publicly released.

Abstract

We study an adversarial bandit problem for entanglement-based quantum-network routing over a modest graph corpus. Alice selects an end-to-end repeater route for an Ekert-91 protocol (E91) representing her move, while Eve selects an attack surface, either edge intercept--resend or repeater memory degradation. Payoffs are drawn from cached SeQUeNCe-simulated E91 transcripts, and Alice accepts a turn when the finite-sample statistic violates the Clauser-Horne-Shimony-Holt (CHSH) bound. Performing adversarial co-learning across 50 structured topologies, we find that learned retention tracks a full-matrix minimax reference closely (Pearson $r=0.99$): under a one-surface Eve action model, bottleneck families have zero retention, while non-bottleneck families follow a $1-1/N$ coverage principle. We then fit decision-tree explanation models to graph-, attack-, and route-level topology-corpus targets and report their faithfulness. Finally, we construct prompt records for local language models to summarize the tree evidence, resulting in an open-source explanation workflow for quantum-repeater network games.

Problem

• quantum repeater networks
• adversarial routing
• entanglement-based protocols
• network robustness
• E91 protocol

Innovation

• adversarial co-learning
• explainable robustness
• quantum repeater networks
• entanglement routing
• CHSH violation