6 papers
Lessons from External Review of DeepMind's Scheming Inability Safety Case
Stephen Barrett, Francisco Javier Campos Zabala, Sean P. Fillingham +4
Safety cases for frontier AI systems should provide a convincing argument, supported by evidence, that the risk of harm is within an acceptable bound. When developers author their…
Understanding: reframing automation and assurance
Robin Bloomfield
Safety and assurance cases risk becoming detached from the understanding needed for responsible engineering and governance decisions. More broadly, the production and evaluation of…
Quantifying Confidence in Assurance 2.0 Arguments
Robin Bloomfield, John Rushby
Confidence is central to safety and assurance cases: how much confidence a decision requires and how much the argument actually provides are both important questions. We present a…
Confidence in Assurance 2.0 Cases
Robin Bloomfield, John Rushby
An assurance case should provide justifiable confidence in the truth of a claim about some critical property of a system or procedure, such as safety or security. We consider how c…
Assurance of AI Systems From a Dependability Perspective
Robin Bloomfield, John Rushby
We outline the principles of classical assurance for computer-based systems that pose significant risks. We then consider application of these principles to systems that employ Art…
Where AI Assurance Might Go Wrong: Initial lessons from engineering of critical systems
Robin Bloomfield, John Rushby
We draw on our experience working on system and software assurance and evaluation for systems important to society to summarise how safety engineering is performed in traditional c…