2024/03/15 by Joshua Clymer, Nick Gabrieli, Clymer, Joshua +4 · 12 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computers and Society (cs.CY) #FOS: Computer and information sciences
paper · pdf · doi:10.48550/arxiv.2403.10462
openalex publication_date 2024/03/15 · openalex created_date 2024/03/19 · openalex updated_date 2026/07/28
As AI systems become more advanced, companies and regulators will make difficult decisions about whether it is safe to train and deploy them. To prepare for these decisions, we investigate how developers could make a 'safety case,' which is a structured rationale that AI systems are unlikely to cause a catastrophe. We propose a framework for organizing a safety case and discuss four categories of arguments to justify safety: total inability to cause a catastrophe, sufficiently strong control measures, trustworthiness despite capability to cause harm, and -- if AI systems become much more powerful -- deference to credible AI advisors. We evaluate concrete examples of arguments in each category and outline how arguments could be combined to justify that AI systems are safe to deploy.