// Comparison

Attacking Network Protocols vs Practical AI Security: Which Should You Read?

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

Advanced

5/52017

A Hacker's Guide to Capture, Analysis, and Exploitation

James Forshaw

James Forshaw, Project Zero veteran, on how to capture, parse, and break protocols from the wire up to the application layer, with a strong focus on building reusable analysis tooling.

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

Anyone who needs to understand traffic, not just see it. Forshaw is the rare Project Zero veteran who can also teach; the book turns network protocol analysis into a learnable craft.

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

Beginners who haven't yet handled a pcap, or readers who only want HTTP/web. The book covers Layer 2 through application-level RPC, and the value compounds the deeper you go.

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

Capturing, parsing, and replaying traffic is one workflow, not three, and Forshaw's tooling-first framing makes that explicit.
Custom-protocol auditing (the part security curricula skip) is the part of the book that pays back hardest, especially for embedded, OT, and proprietary stacks.
The "build your own network analysis tool" chapters teach more about how protocols actually work than any number of Wireshark lessons.

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 Attacking Network Protocols higher (5/5 against 4/5 for Practical AI Security). For most readers, that means Attacking Network Protocols 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.

Attacking Network Protocols and Practical AI Security both cover Offensive, so reading them in sequence reinforces the same material from different angles.

Keep reading

Attacking Network Protocols

→ Alternatives to Attacking Network Protocols → What to read after Attacking Network Protocols