AI, security, safety, resilience, trust.
-
What might go wrong with AI safety and security?
This post looks at what can be learned from engineering critical systems. It summarise a paper written from FAISC and on arxiv.
-
Assurance 2.0
This post provides news on Assurance 2.0. Assurance 2.0 seeks to simplify and make more rigorous, engineering arguments by separating deductive/inductive reasoning, using confirmation theory and CAE Blocks and theories.
-
Defence in depth
This post discusses a new model of defence in depth.
-
Resilience – Type 1 and Type 2
Complex systems will fail, so they need to be resilient. Type 1 deals with known issues we engineer for and Type 2 those we exclude and the unknown unknowns.
Got any paper, tool or book recommendations?
What next? 