Logic-Based Explainability in Machine Learning

Abstract

In recent years, the impact of machine learning (ML) and artificial intelligence (AI) in society has been absolutely remarkable. This impact is expected to continue in the foreseeable future. However, the adoption of AI/ML is also a cause of grave concern. The operation of the most advances AI/ML models is often beyond the grasp of human decision makers. As a result, decisions that impact humans may not be understood and may lack rigorous validation. Explainable AI (XAI) is concerned with providing human decision-makers with understandable explanations for the predictions made by ML models. As a result, XAI is a cornerstone of trustworthy AI. Despite its strategic importance, most work on XAI lacks rigor, and so its use in high-risk or safety-critical domains serves to foster distrust instead of contributing to build muchneeded trust. Logic-based XAI has recently emerged as a rigorous alternative to those other non-rigorous methods of XAI. This paper provides a technical survey of logic-based XAI, its origins, the current topics of research, and emerging future topics of research. The paper also highlights the many myths that pervade non-rigorous approaches for XAI.

Cybercrime Intention Recognition: A Systematic Literature Review

“…The logic-based approach remains the prevailing method in addressing the challenge of IR within DF and related domains. This preference may stem from the domain's inherent need for explainability, as DF investigators are tasked with elucidating the rationale behind a suspect's culpability, and this approach provides a structured framework for explaining both why and how conclusions are derived [44]. Over the past years, this approach has consistently dominated the field as highlighted by Van-Horenbeke et al [11].…”