Lakshya

Book

Securing & Governing AI

The attack surface that is genuinely new, the risks that are old in new clothes, model risk, what audit evidence looks like, the frameworks, and how to be the function that enables.

Assumes AI from First Principles. Read that one first if any of it is unfamiliar.

CHAPTER 8 Prompt injection, and why it is genuinely new The one AI risk with no equivalent in the security canon. Most explanations of it are wrong. CHAPTER 9 What is old wearing new clothes Most of the AI risk register is your existing risk register. Knowing which is which saves enormous effort. CHAPTER 10 Data governance — the actual hard problem Not glamorous, and the source of most real AI incidents to date. CHAPTER 11 Model risk management Banking has governed consequential models for a decade. Most of it transfers directly. CHAPTER 12 Auditing an AI system — what evidence looks like Read this if you have been asked to audit something nobody can quite explain. CHAPTER 13 The frameworks — NIST, ISO 42001, EU AI Act What each is for, which you need, and how not to waste a year. CHAPTER 14 Being the function that enables The argument this whole book is for.