FRAMEWORK-DRIVEN GUIDELINE GENERATION FOR AI ADOPTION: A RISK-BASED PERSPECTIVE

The adoption of artificial intelligence (AI) presents unique risks that existing frameworks inadequately address, including issues of accountability, accuracy, fairness, safety, and privacy. According to AI Incident Database, there is an increase of 156% of published AI incidents from the year 2020 to 2024. This study bridges the gap between reported AI incidents and actionable countermeasures by analyzing an AI incident repository and contextualizing risks with mitigative strategies drawn from the literature. A knowledge graph was developed to integrate contextual data, risks, and countermeasures, enabling the generation of customizable, risk-based guidelines tailored to specific applications and stakeholders. Key findings include the identification of countermeasures for diverse AI risks, emphasizing the need for systematic risk assessment throughout the AI life cycle. The developed prototype serves as both a risk assessment tool and risk reference database in an enhanced enterprise risk management framework which facilitates responsible AI adoption, guiding developers, risk managers, and policymakers in advancing ethical and sustainable AI practices. This work lays the groundwork for automated tools that enhance scalability and usability in addressing AI risks in various organizational contexts.