The principle "Draft Ethics Guidelines for Trustworthy AI" has mentioned the topic "safety" in the following places:
2. The Principle of Non maleficence: “Do no Harm”
By design, AI systems should protect the dignity, integrity, liberty, privacy, safety, and security of human beings in society and at work.
4. Governance of AI Autonomy (Human oversight)
The correct approach to assuring properties such as safety, accuracy, adaptability, privacy, explicability, compliance with the rule of law and ethical conformity heavily depends on specific details of the AI system, its area of application, its level of impact on individuals, communities or society and its level of autonomy.
safety is about ensuring that the system will indeed do what it is supposed to do, without harming users (human physical integrity), resources or the environment.