“Under pressure, an intent verification protects value only when an unread policy can prove it; the adversary already knows this.”

— Professor Kai London, CISO.

Quote card by Professor Kai London reading 'Under pressure, an intent verification protects value only when an unread policy can prove it; the adversary already knows this.'. From the book The AI Control Architecture.
Quote card by Professor Kai London reading 'Under pressure, an intent verification protects value only when an unread policy can prove it; the adversary already knows this.'. From the book The AI Control Architecture.

Under pressure, an intent verification protects value only when an unread policy can prove it; the adversary already knows this. — Kai London (Professor Kai London), CISO. Principle 4707 of 10000 from the book “The AI Control Architecture” — cybersecurity, AI security and OT resilience doctrine. Official sites: professorkailondon.com · kailondon.co.uk

Related: Principle 7207 Principle 9707 Principle 2207

View in gallery (page 48) · About this book