AI Security
How AI systems get attacked, and how to defend them.
Seven chapters on securing AI systems — the new attack surface, the threats that live on it, the layered defences that work, and the governance that proves it. Each pairs a plain-language explanation with optional dive-deepers into the research and the code.
Written for engineers, security professionals, and technical leaders building or buying AI systems. The framing is defensive throughout: understand the attacks in order to stop them. Test only systems you own or are authorised to test.
Chapters
- Chapter 01 · 10 min
The new attack surface
“You hired a brilliant assistant who believes everything they read — and you gave them the keys.”
Read → - Chapter 02 · 13 min
Prompt injection
“A note slipped into the documents you handed your assistant, written as if it came from you.”
Read → - Chapter 03 · 11 min
Data leakage & privacy
“Everything you put in the prompt, you've said out loud in a room you don't control.”
Read → - Chapter 04 · 10 min
Jailbreaks & misuse
“The bouncer follows a script. Find a line the script doesn't cover, and you're inside.”
Read → - Chapter 05 · 11 min
The AI supply chain
“You didn't grow the ingredients. You're trusting every farm, truck, and warehouse you never saw.”
Read → - Chapter 06 · 12 min
Defending AI systems
“Build a castle, not a wall. Walls fall; layers buy you time to notice and respond.”
Read → - Chapter 07 · 11 min
Governance & assurance
“Locks keep honest people honest. Governance is the paperwork that proves you fitted the locks.”
Read →