// Comparison

Building Secure and Reliable Systems vs Practical AI Security: 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

5/52020

Best Practices for Designing, Implementing, and Maintaining Systems

Heather Adkins, Betsy Beyer, Paul Blankinship, Piotr Lewandowski, Ana Oprea, Adam Stubblefield

Google's site-reliability and security teams jointly write down what it actually takes to build systems that are both safe and dependable, from threat models and design reviews to rollback culture and crisis response.

Advanced

4/52026

Practical AI Security

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.

Read this if

Staff-and-up engineers, SREs, and security leads designing or operating systems where reliability and security must be argued for in the same room. The book treats safety and security as the same engineering discipline, which is the right model and almost nobody else publishes it.

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.

Skip this if

Readers who want a tooling tutorial or vendor-neutral checklists. The case studies are Google-shaped, and the patterns assume you have the discipline (postmortems, code review, paved roads) to execute them. If your org cannot stop a deploy, half the book will read as aspirational.

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.

Key takeaways

Reliability and security share a common substrate: both are about designing for failure modes you cannot fully predict, and both decay if not exercised.
Recovery, not prevention, is the core skill of mature security organizations; the rollback, response, and recovery chapters are the heart of the book.
Most security wins come from boring infrastructure (paved roads, default-secure libraries, code review, sandboxing) rather than detection magic.

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.

How they compare

We rate Building Secure and Reliable Systems higher (5/5 against 4/5 for Practical AI Security). For most readers, that means Building Secure and Reliable Systems 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.

Building Secure and Reliable Systems and Practical AI Security both cover Defensive, so reading them in sequence reinforces the same material from different angles.

Keep reading

Building Secure and Reliable Systems

→ Alternatives to Building Secure and Reliable Systems → What to read after Building Secure and Reliable Systems