A Systematic Literature Review on AI Safety: Identifying Trends, Challenges, and Future Directions

Abstract

Artificial intelligence (AI) is revolutionizing many aspects of our lives, except it raises fundamental safety and ethical issues. In this survey paper, we review the current state of research on safe and trustworthy AI. This work provides a structured and systematic overview of AI safety. In which, we emphasize the significance of designing AI systems with safety focus, encompassing elements from data management, model development, and deployment. We underscore the need for AI systems to align with human values and operate within mounted ethical frameworks. In addition, we notice the need for a complete safety framework that courses the development and implementation of AI systems, ensuring they do not inadvertently cause damage to humans. Our results show that AI safety is associated with model learning techniques, verification and validation methods, failure modes, and managing AI autonomy. As discussed in the literature, the main concerns include explainability, interpretability, robustness, reliability, fairness, bias, and adversarial attacks.

Keywords

• AI safety
• robustness
• trustworthy AI
• fairness and bias
• explainability and interpretability