On Explainable AI Solutions for Targeting in Cyber Military Operations

Abstract

Nowadays, it is hard to recall a domain, system, or problem that does not use, embed, or could be tackled through AI. From early stages of its development, its techniques and technologies were successfully implemented by military forces for different purposes in distinct military operations. Since cyberspace represents the last officially recognized operational battlefield, it also offers a direct virtual setting for implementing AI solutions for military operations conducted inside or through it. However, planning and conducting AI-based cyber military operations are actions still in the beginning of development. Thus, both practitioner and academic dedication isrequired since the impact of their use could have significant consequences which requires that the output of such intelligent solutions is explainable to the engineers developing them and also to their users e.g., military decision makers. Hence, this article starts by discussing the meaning of explainable AI in the context of targeting in military cyber operations, continues by analyzing the challenges of embedding AI solutions (e.g., intelligent cyber weapons) in different targeting phases, and is structuring them in corresponding taxonomies packaged in a design framework. It does that by crossing the targeting process focusing on target development, capability analysis, and target engagement. Moreover, this research argues that especially in such operations carried out in silence and at incredible speed, it is of major importance that the military forces involved are aware of the following. First, the decisions taken by theintelligent systems embedded. Second, are not only aware, but also able to interpret the results obtained from the AI solutions in a proper, effective, and efficient way. From there, this research draws possible technological and humanoriented methods that facilitate the successful implementation of XAI solutions for targeting in military cyber operations.