Explainable Artificial Intelligence on the Battlefield (Military-XAI, MXAI) : Research for Military Application Scenarios
한국과학기술원(KAIST) 연구교수, Keun-Ha Choi, Jeong Jae-Won, Woosin Lee, Jongchul Ahn, Mikyoung Lee · 한국방위산업학회지 · 2023
The most significant weakness of AI technology is the lack of explainability of the results obtained by AI. The technology that has emerged to compensate for this weakness of traditional AI is eXplainable AI (XAI). XAI is attracting great attention in applications where the reliability of inference results is important, such as healthcare, defense, law, and has recently been judged to be indispensable for military applications. The U.S. Defense Advanced Research Projects Agency (DARPA) is actively promoting the application of XAI in the military field by operating the XAI Program, in which 11 universities and research institutes such as UC Berkeley and Carnegie Mellon University participate, but in the case of the Korean military, research on XAI development is underdeveloped due to the focus on developing AI capabilities. In this paper, we also examine the concept and methodology of XAI and propose a method for applying XAI technology that can be applied to AI technology for each battlefield functions. The concept and recent technology of XAI are summarized, and the concept of XAI operation and application scenario of AI that is expected to be applied to the weapon system for each battlefield function is presented.