// Comparison

Intelligence artificielle, cybersécurité et cyberdéfense vs Practical AI Security: Which Should You Read?

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

Advanced

3/52020

Intelligence artificielle, cybersécurité et cyberdéfense

Daniel Ventre

An academic examination of how artificial intelligence reshapes cybersecurity and cyberdefence — opportunities, threats and strategic implications — by France's most prolific cyberwar scholar.

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

Researchers and analysts who want a rigorous, referenced treatment of the AI-cyber intersection from a strategic and defence standpoint.

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

Practitioners wanting applied ML-security techniques; it's an academic, strategy-oriented analysis, not a hands-on ML or detection guide.

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

An academic treatment of the AI/cybersecurity intersection from a strategic-defence angle.
Ventre is France's most prolific cyberwar scholar — heavily referenced and systematic.
Conceptual and strategic, not a hands-on machine-learning-for-security manual.

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 Practical AI Security higher (4/5 against 3/5 for Intelligence artificielle, cybersécurité et cyberdéfense). For most readers, that means Practical AI Security is the primary pick and Intelligence artificielle, cybersécurité et cyberdéfense is a useful follow-up.

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

Intelligence artificielle, cybersécurité et cyberdéfense and Practical AI Security both cover Machine Learning, Defensive, so reading them in sequence reinforces the same material from different angles.

Keep reading