5 citations · 15 across the 4 of their papers we have counts for
4 papers
Mapping Technical Safety Research at AI Companies: A literature review and incentives analysis
Oscar Delaney, Oliver Guest, Zoe Williams
As AI systems become more advanced, concerns about large-scale risks from misuse or accidents have grown. This report analyzes the technical research into safe AI development being…
Adapting cybersecurity frameworks to manage frontier AI risks: A defense-in-depth approach
Shaun Ee, Joe O'Brien, Zoe Williams +3
The complex and evolving threat landscape of frontier AI development requires a multi-layered approach to risk management ("defense-in-depth"). By reviewing cybersecurity and AI fr…
Coordinated Disclosure of Dual-Use Capabilities: An Early Warning System for Advanced AI
Joe O'Brien, Shaun Ee, Jam Kraprayoon +3
Advanced AI systems may be developed which exhibit capabilities that present significant risks to public safety or security. They may also exhibit capabilities that may be applied…
Deployment Corrections: An incident response framework for frontier AI models
Joe O'Brien, Shaun Ee, Zoe Williams
A comprehensive approach to addressing catastrophic risks from AI models should cover the full model lifecycle. This paper explores contingency plans for cases where pre-deployment…