// Comparison

Practical AI Security vs Security Chaos Engineering: Which Should You Read?

Two cybersecurity books on Defensive, compared honestly: who each is for, what each does best, and which to read first.

Advanced

4/52026

A Hands-on Guide to Attacking, Defending, and Securing Modern AI Systems

Harriet Farlow

The founder of an AI-security firm, with a PhD in adversarial machine learning, walks from how models fail to how they're exploited to how they're defended and audited, with over 30 hands-on Python demos.

Advanced

5/52023

Security Chaos Engineering

Sustaining Resilience in Software and Systems

Kelly Shortridge, Aaron Rinehart

Kelly Shortridge and Aaron Rinehart on treating security as a property of complex adaptive systems: instead of preventing failure, you continuously simulate it, and design the organization to learn from each result.

Read this if

Security practitioners and ML engineers who need practical, hands-on grounding in attacking and defending AI systems rather than a survey of the field. Farlow has led AI-security assessments for Fortune 500s and government agencies, and the book is built from that assessment experience.

Security architects, SREs, and platform engineers ready to abandon the prevention-first frame. Particularly strong for organizations that already practice chaos engineering for reliability and want to extend the discipline to security; the book is the bridge.

Skip this if

Readers who want a conceptual or policy-level introduction to AI risk; this is a hands-on technical guide with Python demos throughout, not an AI-governance primer. Also assumes baseline ML and security fundamentals rather than teaching either from zero.

Practitioners working in heavily regulated environments where intentional production faults are not legal, or smaller organizations without the operational maturity to run game days safely. Also a poor first security book: it assumes you know what threat models, blast radius, and feedback loops are.

Key takeaways

First book in this catalog to treat AI/ML systems as a first-class attack surface in their own right, not a feature bolted onto traditional appsec.
Structured around the full lifecycle: how models fail, how failures become exploits, then how to defend and audit against both.
Over 30 hands-on Python demos keep the material concrete rather than theoretical — attacks and defenses you can actually run.

Security and reliability share the same root engineering problem: how to keep complex systems within tolerable bounds when the failure surface is unbounded.
Decision trees and effort-vs-impact analysis are operationalizable artifacts, not just blog material; the book teaches you to actually use them.
Continuous experimentation is more honest than tabletop exercises: production tells you what is true, runbooks tell you what someone wished were true.

How they compare

We rate Security Chaos Engineering higher (5/5 against 4/5 for Practical AI Security). For most readers, that means Security Chaos Engineering is the primary pick and Practical AI Security is a useful follow-up.

Both books target advanced-level readers, so the choice is about topic, not difficulty.

Practical AI Security and Security Chaos Engineering both cover Defensive, so reading them in sequence reinforces the same material from different angles.

Keep reading

Practical AI Security

→ Alternatives to Practical AI Security → What to read after Practical AI Security