Online safety by design: towards user-centric development of safer AI-based systems.

In this opinion piece, we present the view that the safety and security of end users should be placed at the heart of the design and development of any AI-based system deployed on an online service to ensure that risks of harm are minimized. We also posit that while well-crafted regulatory frameworks are necessary to ensure user safety, the growing awareness among users of issues related to trust and safety creates an additional incentive for providers of online services to prioritize user well-being. We provide a brief overview of how online safety relates to several widely used systems on online services that utilize or interact with AI, discussing examples of potential risks of harm, which may be enabled or reinforced by these systems, alongside techniques for mitigating these harms. Future challenges and opportunities across these areas are discussed, along with a summary of how user, device and platform diversity can impact users' experiences with AI-based systems on online services. This article is part of the theme issue 'Safe, secure and robust AI for safety-critical systems'.