LATENT LIBRARY ETHICS & GOVERNANCE AI Security Attacks, Defences and Secure Designfor AI Systems LATENT LIBRARY EDITORIAL

AI Security

Attacks, Defences and Secure Design for AI Systems

Latent Library Editorial

IntroductionIntroduction

AI systems add new attack surfaces to familiar software. Attackers no longer need to find a buffer overflow or a weak password if they can poison the data a model learns from, craft an input that fools it, extract its training data or slip instructions into a document that an AI assistant will read and obey. When AI systems can call tools, send messages or move money, these attacks have real consequences.

This book explains the threats and the defences that work. It covers threat modelling for AI, prompt injection and jailbreaks, data poisoning and backdoors, adversarial examples, model and data extraction, privacy attacks, supply-chain risks, and the special risks of agents with tools. Defensive chapters cover secure architecture, least privilege, input and output controls, monitoring, red teaming and incident response.

The focus is defensive and practical: understanding attacks so that you can design systems that resist them. No offensive exploitation recipes are included.

How the book is organised

Chapter 1Why AI Security Is Different

Traditional security separates code (trusted instructions) from data (untrusted input). Language models blur this line: they take instructions written in natural language, and any text they read, whether a web page, an email or a document, can contain instructions. Models are also probabilistic, so defences that rely on the model "refusing" are never absolute.

Other differences:

You have reached the end of the free sample.
The full book continues with 65 more chapters, plus the appendices.

Get the full book