Jamming may become a serious threat in Internet of Things networks of battery-powered nodes, as attackers can disrupt packet delivery and significantly reduce the lifetime of the nodes. In this work, we model an active defense scenario in which an energy-limited node uses power control to defend itself from a malicious attacker, whose energy constraints may not be known to the defender. The interaction between the two nodes is modeled as an asymmetric Bayesian game where the victim has incomplete information about the attacker. We show how to derive the optimal Bayesian strategies for both the defender and the attacker, which may then serve as guidelines to develop and gauge efficient heuristics that are less computationally expensive than the optimal strategies. For example, we propose a neural-network-based learning method that allows the node to effectively defend itself from the jamming with a significantly reduced computational load. The outcomes of the ideal strategies highlight the tradeoff between node lifetime and communication reliability and the importance of an intelligent defense from jamming attacks.

中文翻译：

---

具有学习对抗策略的能量消耗干扰攻击的博弈论分析

干扰可能成为电池供电节点的物联网网络的严重威胁，因为攻击者可以破坏数据包传输并显着缩短节点的寿命。在这项工作中，我们模拟了一个主动防御场景，其中能量有限的节点使用功率控制来保护自己免受恶意攻击者的攻击，防御者可能不知道其能量限制。两个节点之间的交互被建模为非对称贝叶斯博弈，其中受害者对攻击者的信息不完整。我们展示了如何为防御者和攻击者推导出最佳贝叶斯策略，然后可以作为开发和衡量有效启发式算法的指南，这些启发式算法的计算成本低于最佳策略。例如，我们提出了一种基于神经网络的学习方法，该方法允许节点有效地保护自己免受干扰，同时显着减少计算负载。理想策略的结果突出了节点寿命和通信可靠性之间的权衡以及智能防御干扰攻击的重要性。