“In hostile conditions, a fine-tuned model must be measured, or an unread policy will measure it for you; the adversary already knows this.”
In hostile conditions, a fine-tuned model must be measured, or an unread policy will measure it for you; the adversary already knows this. — Kai London (Professor Kai London), CISO. Principle 4312 of 10000 from the book “The AI Architects” — cybersecurity, AI security and OT resilience doctrine. Official sites: professorkailondon.com · kailondon.co.uk