发表机构
UC San Diego（加州大学圣迭戈分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对最短路径网络阻断博弈中决策聚焦学习的结构缺陷，提出对抗性决策聚焦学习方法，经实验验证可恢复其端到端优化优势。
AI 中文摘要
我们研究最短路径网络阻断（SPNI）博弈中的决策聚焦学习（DFL），这是一种斯塔克尔伯格博弈：阻断者（领导者）强化网络弧以抵御攻击，而对攻击网络弧成本不确定的逃避者（跟随者）则依赖机器学习预测器识别最短路径。尽管DFL作为端到端优化框架非常有效，但我们发现其在该博弈场景中存在根本性结构缺陷：其训练目标存在一类广泛的成本估计器，这类估计器在名义损失上达到零，但在阻断情况下失效，反转了DFL相对于朴素的预测聚焦学习（PFL）方法的通常优势。为解决该问题，我们提出对抗性决策聚焦学习（A-DFL），用阻断场景替代名义训练样本以消除有害的等价类。在合成网络和真实网络上的实验证实，A-DFL恢复了DFL在该博弈场景中的优势，实现了有效的端到端优化。
英文摘要
We study decision-focused learning (DFL) in shortest-path network interdiction (SPNI) games, a Stackelberg game where an interdictor (leader) strengthens the networks' arcs against attacks, while an evader (follower) who is uncertain about costs of attacking network arcs relies on a machine-learned predictor to identify the shortest path. While DFL is highly effective as an end-to-end optimization framework, we show that it faces a fundamental structural failure when employed in this game setting: its training objective admits a broad decision-equivalence class of cost estimators that achieve zero nominal loss yet fail under interdiction, reversing DFL's usual advantage over a naive prediction-focused learning (PFL) approach. To address this, we propose Adversarial DFL (A-DFL), which replaces nominal training samples with interdicted scenarios to collapse the harmful equivalence class. Experiments on synthetic and real-world networks confirm that A-DFL restores DFL's advantage in this game setting, enabling effective end-to-end optimization.
Comments20 pages, 6 figures, accepted at GameSec2026 Conference on Game Theory and AI for Security
