The threats posed by evolving cyberattacks have led to increased research related to software systems that can self-protect. One topic in this domain is Moving Target Defense (MTD), which changes software characteristics in the protected system to make it harder for attackers to exploit vulnerabilities. However, MTD implementation and deployment are often impacted by run-time uncertainties, and existing MTD decision-making solutions have neglected uncertainty in model parameters and lack self-adaptation. This paper aims to address this gap by proposing an approach for an uncertainty-aware and self-adaptive MTD decision engine based on Partially Observable Markov Decision Process and Bayesian Learning techniques. The proposed approach considers uncertainty in both state and model parameters; thus, it has the potential to better capture environmental variability and improve defense strategies. A preliminary study is presented to highlight the potential effectiveness and challenges of the proposed approach.

翻译：不断演变的网络攻击威胁促使对能够自我保护的软件系统的研究日益增多。该领域的一个研究方向是移动目标防御（MTD），它通过改变受保护系统的软件特性，使攻击者更难利用漏洞。然而，MTD的实施和部署常受运行时不确定性影响，现有MTD决策方案忽视了模型参数的不确定性，且缺乏自适应能力。本文旨在弥补这一空白，提出一种基于部分可观测马尔可夫决策过程与贝叶斯学习技术的不确定性感知自适应MTD决策引擎。该方案同时考虑状态和模型参数的不确定性，因此有望更好地捕捉环境变化并改进防御策略。本文通过初步研究展示了该方法的潜在有效性与面临的挑战。