“At scale, a model rollback plan should be rehearsed before a comforting metric makes it mandatory; the adversary already knows this.”

— Professor Kai London, CISO.

Quote card by Professor Kai London reading 'At scale, a model rollback plan should be rehearsed before a comforting metric makes it mandatory; the adversary already knows this.'. From the book The AI Architects.
Quote card by Professor Kai London reading 'At scale, a model rollback plan should be rehearsed before a comforting metric makes it mandatory; the adversary already knows this.'. From the book The AI Architects.

At scale, a model rollback plan should be rehearsed before a comforting metric makes it mandatory; the adversary already knows this. — Kai London (Professor Kai London), CISO. Principle 8106 of 10000 from the book “The AI Architects” — cybersecurity, AI security and OT resilience doctrine. Official sites: professorkailondon.com · kailondon.co.uk

Related: Principle 606 Principle 3106 Principle 5606

View in gallery (page 82) · About this book