<div class="raw-html-embed"><a href="https://libratech.ai/ch/?utm_source=partner&amp;utm_medium=website&amp;utm_campaign=wkch_libra_prsp_staempfli_07_2026
">Stämpfli Fachinhalte - jetzt im rechtssicheren Libra All-In-One AI Workspace verfügbar - Jetzt kostenlos testen!</a></div>

Über uns

À propos de nous

Nachhaltigkeit

Durabilité

Open Access

Karriere

Carrière

Aboverträge Kündigen

Résiliation d’abonnement

Vertrag widerrufen

Résiliation de contrat 

Datenschutz

Protection des données

Impressum

Mentions légales

Zahlung und Lieferung

Paiement et livraison

Libra

Was ist Libra?

C'est quoi Libra ?

Kostenlos testen

Tester gratuitement

LEXIA

LEXIA Arbeitsrecht

Was ist LEXIA?

C'est quoi LEXIA ?

LEXIA Familienrecht

Zeitschriften

Revues

recht

Pflegerecht

ZBJV

forumpoenale

ZStrR

Anwaltsrevue

Revue de l'avocat

RSAS

FamPra.ch

ASYL

Life Science Recht

BlAR

Sachbuch

Livres spécialisés

LOKI

Semaphor

Fokusthemen

Focus

Thema

Recht studieren

Arbeitsrecht

Droit du travail

Studium

Études

Familienrecht

Droit de la famille

Sozialversicherungsrecht

Droit des assurances sociales

Strafrecht

Droit pénal

Aktienrecht

Droit des sociétés anonymes

Publikationen

Publications

Literatur

Digitales Angebot

Bücher

Livres

Buchreihen

Collections

Onlinemodule LEXIA

Modules en ligne LEXIA

recht.ch

Studienliteratur

Littérature pour les études

Dienstleistungen

Services

Dienstleistungen für

Corporate Books

Publishing Lösungen

Aktuelles

Geschäftskunden

Professionnels

Corporate Publishing

Content solutions

Buchhandlungen

Librairies

Veranstaltungen

Événements

Presse

Dozierende

Enseignants

Studierende

Étudiants

Inserierende

Annonceurs

Newsletter

Blog

Autorinnen/Autoren

Auteurs

Unsere Schreibenden

Hilfe

Unsere Autorinnen und Autoren

Liste

Autorenlounge

Espace des auteurs

Bei uns publizieren

Publier chez nous

Autorenstimmen

Témoignages

Verlag

Éditions

Themen

Mehr wissen

Mitarbeitende

Collaborateurs

Geschichte

Histoire

Vision und Mission

Vision et mission

Unser Magazin

Notre magazine

Unternehmenskultur

Culture d'entreprise

Partner

Partenaires

Kontakt

Contact

Shop

Schweizer Recht

Ausländisches Recht

Über unseren Shop

Neuerscheinungen

Nouveautés

Unsere Funktionen

Nos fonctions

Vorankündigungen

À paraître

Nach Rechtsgebiet

Par domaine juridique

Kommentare

Commentaires

Gesamtkatalog

Catalogue complet

Hyndman R: Forecasting

Forecasting

Principles and Practice, the Pythonic Way

Apress Pocket Guides

Unlock the secrets of practical data analysis with the Data Flow Map framework—a game-changing approach that transcends tools and platforms.&nbsp;This book isn’t just another programming manual; it’s a guide to thinking and communicating about data at a higher level. Whether you're working with spreadsheets, databases, or AI-driven models, you'll learn how to express your analytics in clear, common language that anyone can understand.
In today’s data-rich world, clarity is the real challenge. Technical details often obscure insights that could drive real impact. The Data Flow Map framework simplifies complexity into three core motions: source, focus, and build. The first half of the book explores these concepts through illustrations and stories. The second half applies them to real-world datasets using tools like Excel, SQL, and Python, demonstrating how this approach adapts seamlessly across platforms and use cases.
A vital resource for analysts at any level, this book offers a practical, tool-agnostic approach to data analysis. With hands-on examples and a universal mental model, you’ll gain the confidence to tackle any dataset, align your team, and deliver insights that matter. Whether you're a beginner or a seasoned pro, the Data Flow Map framework will transform how you approach data analytics.
What You Will Learn
<ul>
<li>Grasp essential elements applicable to every data analysis workflow</li>
<li>Adapt quickly to any dataset, tool, or platform</li>
<li>Master analytic thinking at a higher level</li>
<li>Use analytics patterns to better understand the world</li>
<li>Break complex analysis into manageable, repeatable steps</li>
<li>Iterate faster to uncover deeper insights and better solutions</li>
<li>Communicate findings clearly for better decision-making</li>
</ul>

Unlock the secrets of practical data analysis with the Data Flow Map framework—a game-changing approach that transcends tools and platforms.&nbsp;This book isn’t just another programming manual; it’s a guide to thinking and communicating about data at a higher level. Whether you're working with spreadsheets, databases, or AI-driven models, you'll learn how to express your analytics in clear, common language that anyone can understand.In today’s data-rich world, clarity is the real challenge.&nbsp;Technical details often obscure insights that could drive real impact. The Data Flow Map framework simplifies complexity into three core motions:&nbsp;source, focus, and build. The first half of the book explores these concepts through illustrations and stories. The second half applies them to real-world datasets using tools like&nbsp;Excel, SQL, and Python, showing how the framework works across platforms and use cases.A vital resource for analysts at any level, this book offers a practical, tool-agnostic approach to data analysis. With hands-on examples and a universal mental model, you’ll gain the confidence to tackle any dataset, align your team, and deliver insights that matter. Whether you're a beginner or a seasoned pro, the Data Flow Map framework will transform how you approach data analytics.What You Will Learn<ul><li>Grasp essential elements applicable to every data analysis workflow</li><li>Adapt quickly to any dataset, tool, or platform</li><li>Master analytic thinking at a higher level</li><li>Use analytics patterns to better understand the world</li><li>Break complex analysis into manageable, repeatable steps</li><li>Iterate faster to uncover deeper insights and better solutions</li><li>Communicate findings clearly for better decision-making</li></ul>Who This Book Is ForAspiring data professionals and experienced analysts, from beginners to seasoned data engineers, focused on data collection, analysis, and decision making

A Practical Guide to Clear and Creative Analytics in Any Data Environment

The Data Flow Map

This book is a complete, hands-on guide to designing, training, and deploying your own Large Language Models (LLMs)—from the foundations of tokenization to the advanced stages of fine-tuning and reinforcement learning. Written for developers, data scientists, and AI practitioners, it bridges core principles and state-of-the-art techniques, offering a rare, transparent look at how modern transformers truly work beneath the surface.
Starting from the essentials, you’ll learn how to set up your environment with Python and PyTorch, manage datasets, and implement critical fundamentals such as tensors, embeddings, and gradient descent. You’ll then progress through the architectural heart of modern models, covering RMS normalization, rotary positional embeddings (RoPE), scaled dot-product attention, Grouped Query Attention (GQA), Mixture of Experts (MoE), and SwiGLU activations, each explored in depth and built step by step in code. As you advance, the book introduces custom CUDA kernel integration, teaching you how to optimize key components for speed and memory efficiency at the GPU level—an essential skill for scaling real-world LLMs. You’ll also gain mastery over the phases of training that define today’s leading models:
<ul>
<li>Pretraining - Building general linguistic and semantic understanding.

</li><li>Midtraining - Expanding domain-specific capabilities and adaptability.

</li><li>Supervised Fine-Tuning (SFT) - Aligning behavior with curated, task-driven data.

</li><li>Reinforcement Learning from Human Feedback (RLHF) - Refining responses through reward-based optimization for human alignment.



The final chapters guide you through dataset preparation, filtering, deduplication, and training optimization, culminating in model evaluation and real-world prompting with a custom TokenGenerator for text generation and inference.
By the end of this book, you’ll have the knowledge and confidence to architect, train, and deploy your own transformer-based models, equipped with both the theoretical depth and practical expertise to innovate in the rapidly evolving world of AI.
What You’ll Learn
<ul>
<li>How to configure and optimize your development environment using PyTorch

</li><li>The mechanics of tokenization, embeddings, normalization, and attention mechanisms.

</li><li>How to implement transformer components like RMSNorm, RoPE, GQA, MoE, and SwiGLU from scratch.

</li><li>How to integrate custom CUDA kernels to accelerate transformer computations.

</li><li>The full LLM training pipeline: pretraining, midtraining, supervised fine-tuning, and RLHF.

</li><li>Techniques for dataset preparation, deduplication, model debugging, and GPU memory management.

</li><li>How to train, evaluate, and deploy a complete GPT-like architecture for real-world tasks.





Who this book is for:
Software developers, data scientists, machine learning engineers and AI enthusiasts looking to build their models from scratch.
</li></ul></li></ul>

Design, Train, and Deploy LLMs with PyTorch

Building Large Language Models from Scratch

Palgrave Texts in Econometrics

This edited collection commemorates and builds upon the work of prominent Greek scholar in econometrics, Professor Efthymios (Mike) Tsionas. Including previously published work by Professor Tsionas, as well as original research from scholars in his related fields, this book makes a significant contribution to applied econometrics.Within a single volume, readers will have the opportunity to explore the impactful contributions made by Mike Tsionas throughout his academic career. Chapters cover four key sections, including recent econometric method developments, Bayesian methods, stochastic frontier analysis and inefficiency, and macroeconomic applications. The book features contributions from globally recognized scholars in econometrics, with significant policy relevance. This will be a valuable resource for students and researchers of econometrics, specifically working on topics including Bayesian inference, productivity and inefficiency, macro-finance and banking.Stelios Arvanitis
 &nbsp;is Professor of Econometrics at Athens University of Economics and Business, Greece.
 Ioannis Bournakis
 &nbsp;is Associate Professor of Economics at SKEMA Business School, Lille, France.
 Dimitris K. Christopoulos
 &nbsp;is Professor of Economics at Athens University of Economics and Business, Greece.
 Elias Tzavalis&nbsp;
 is Professor of Economics at Athens University of Economics and Business, Greece.

This edited collection commemorates and builds upon the work of prominent Greek scholar in econometrics, Professor Efthymios (Mike) Tsionas. Including previously published work by Professor Tsionas, as well as original research from scholars in his related fields, this book makes a significant contribution to applied econometrics.Within a single volume, readers will have the opportunity to explore the impactful contributions made by Mike Tsionas throughout his academic career. Chapters cover four key sections, including recent econometric method developments, Bayesian methods, stochastic frontier analysis and inefficiency, and macroeconomic applications. The book features contributions from globally recognized scholars in econometrics, with significant policy relevance. This will be a valuable resource for students and researchers of econometrics, specifically working on topics including Bayesian inference, productivity and inefficiency, macro-finance and banking.

Theory and Practice in Memory of Efthymios (Mike) Tsionas

Topics in Applied Econometrics

Python: In 21 Tagen die gefragte Programmiersprache lernen, spannende Projekte realisieren und neue berufliche Perspektiven eröffnen
 Sie sind fasziniert von Codes, Programmieren und effizienter Arbeitsorganisation? Und wollen endlich selbst in die Welt der Programmiersprachen einsteigen? Und das Ganze soll dazu anfängertauglich, step-by-step und anwendungsorientiert sein? Bittesehr - hier kommt Ihr persönlicher 21-Tage-Fahrplan zu fundierten Python-Fähigkeiten für Alltag, Studium oder Büro!Wer Python-Code beherrscht und gezielt für seine Zwecke einsetzen kann, ist in der modernen Arbeitswelt absolut im Vorteil: Es gibt kaum einen Job, in dem Sie mit soliden Programmierkenntnissen Prozessabläufe nicht optimieren und effizienter gestalten können, und dazu eröffnet Ihnen die Fähigkeit völlig neue berufliche Perspektiven. Doch auch das Alltagsmanagement kommt ohne digitale Unterstützung kaum mehr aus - und wie Sie sich die genau auf Ihre Bedürfnisse zugeschnitten selbst programmieren, zeigt Ihnen dieses Buch. Es führt Sie zunächst verständlich in die Grundlagen ein, zeigt Ihnen, wie Code überhaupt funktioniert, und erweitert dann Schritt für Schritt Ihre Kenntnisse sowie praktischen Anwendungsfähigkeiten. Sie lernen grundlegende Datenstrukturen ebenso kennen wie objektorientierte Programmierung und beherrschen schließlich auch fortgeschrittene Konzepte wie Dekoratoren oder List Comprehensions. Klingt (noch) alles wie Chinesisch für Sie? Keine Sorge! Dieser Praxisratgeber richtet sich gezielt an Laien ohne Vorkenntnisse und bringt Ihnen die faszinierende Welt des Codes einfach erklärt und in genau Ihrem Tempo nahe.Tag 1-9: Einführung und Grundlagen:
 Lernen Sie die Python-Entwicklungsumgebung (IDE) kennen, machen Sie sich mit den ersten Programmierungsgrundlagen vertraut und entdecken Sie grundlegende Datenstrukturen wie Listen, Tupel oder Sets.
 Tag 10-15: OOP, Dateioperationen &amp; Module:
 Steigen Sie in die objektorientierte Programmierung mit Vererbung, Polymorphismus und Kapselung ein und erlernen Sie den Umgang mit verschiedenen Dateiformaten und Modulen.
 Tag 16-18: Fortgeschrittene Konzepte:
 Generatoren und Iteratoren, Fehlerbehandlung und Ausnahmen oder Lambda-Ausdrücke - mit fortgeschrittenen Profi-Anwendungen holen Sie das Maximum aus Python heraus.
 Tag 19-21: Spannende Praxisprojekte:
 Setzen Sie nützliche Projekte wie IBAN-Prüfer, Datei-Organizer, Zufalls-Entscheidungshelfer oder Mini-KI für Chatantworten mit klaren, präzisen Anleitungen ganz einfach in die Tat um.
 Dieses Buch ist Ihr perfekter Einstieg in das faszinierende und zukunftsweisende Universum des Programmierens und macht Sie in kürzester Zeit zum Python-Profi. Ob Alltag erleichtern, Büroaufgaben vereinfachen oder Arbeitsprozesse optimieren - hier finden Sie das Werkzeug für jedes Projekt.Also, worauf warten Sie noch?
 Klicken Sie nun auf "Jetzt kaufen mit 1-Click" und investieren Sie Ihre Zeit in eine Fähigkeit, die Sie in Beruf &amp; Karriere wirklich weiterbringt!

Das Python Buch für Einsteiger: In 21 Tagen Schritt für Schritt Python programmieren lernen ohne Vorwissen - inkl. 14 Praxisprojekte, IDE-Setup, 50 Standardbefehle uvm

Statistical skills are essential for analysing data and ensuring optimal business operation and efficiency. In this clear and concise textbook, Les Oakshott and Kathy Kotiadis guide students through key quantitative techniques, from basic maths and statistics through to advanced topics such as hypothesis testing and linear programming. Grounded in the everyday realities of business, this textbook introduces each chapter with an engaging case study to highlight how organisations operationalise these techniques, ranging from the growth of China's economy and a Covid-19 infection survey to goal scoring at Euro 2024 and the effect of global warming on the occurrence of salmonella in Singapore. New to this edition: -Links the UN Sustainable Development Goals to quantitative techniques -Greater emphasis on Excel to enable seamless transition to blended learning approaches -Walk-through videos of key processes hosted on the companion website This is the essential textbook for delivering quantitative methods and business statistics modules to students of mixed maths abilities across undergraduate and postgraduate levels. Accompanying online resources for this title can be found at bloomsbury.pub/essential-quantitative-methods-8e. These resources are designed to support teaching and learning at no extra cost.

for Business, Management and Finance

Essential Quantitative Methods

De Gruyter Textbook

This book is a textbook about calculus of one variable. It contains proofs of all the theorems, propositions etc but also Python codes in order to solve many calculus problems. To produce these codes we use AI and show to the reader how to do that.&nbsp;
This book aims to supplement the existing bibliography concerning single-variable calculus. Material including Python code for both symbolic and approximate computations. Our goal is to appropriately use artificial intelligence to generate this code and demonstrate to students how this is approximately done. This book is extremely useful for first-year science students, their professors, and others.

This book is a textbook about calculus of one variable. It contains proofs of all the theorems, propositions etc but also Python codes in order to solve many calculus problems. To produce these codes we use AI and show to the reader how to do that.&nbsp;This book aims to supplement the existing bibliography concerning single-variable calculus. Material including Python code for both symbolic and approximate computations. Our goal is to appropriately use artificial intelligence to generate this code and demonstrate to students how this is approximately done. This book is extremely useful for first-year science students, their professors, and others.

with Python and AI

Calculus of One Variable

This book equips AI developers, machine learning engineers, and software architects with the knowledge and tools needed to design, build, and deploy scalable autonomous agents. Beginning with foundational concepts in LLMs and agent architectures, the book transitions into hands-on design patterns and real-world implementation guidance. Readers will follow practical Python examples using cutting-edge frameworks like LangChain and AutoGen, with full reproducible code available on GitHub.
Emphasizing engineering essentials scalability, interoperability, observability, and ethics the book dives into multi-agent coordination, including emerging protocols such as MCP and A2A. It wraps up with compelling case studies from customer service bots to multi-agent analytics systems demonstrating how to build secure, stable, and trust-aligned AI agents. This guide bridges theory with practice for the modern AI practitioner.
You Will:
<ul>
<li>Discover reusable patterns such as reactors, planners, and tool-using agents that power effective autonomous systems.</li>
<li>Learn to build agents using Python with popular frameworks like LangChain and AutoGen, complete with reproducible GitHub code.</li>
<li>Dive into cutting-edge coordination mechanisms (e.g., MCP, A2A) that enable agents to collaborate and assign tasks dynamically.</li>
</ul>
&nbsp;
This book is for : Software Architects &amp; System Designers
&nbsp;

This book equips AI developers, machine learning engineers, and software architects with the knowledge and tools needed to design, build, and deploy scalable autonomous agents. Beginning with foundational concepts in LLMs and agent architectures, the book transitions into hands-on design patterns and real-world implementation guidance. Readers will follow practical Python examples using cutting-edge frameworks like LangChain and AutoGen, with full reproducible code available on GitHub.Emphasizing engineering essentials scalability, interoperability, observability, and ethics the book dives into multi-agent coordination, including emerging protocols such as MCP and A2A. It wraps up with compelling case studies from customer service bots to multi-agent analytics systems demonstrating how to build secure, stable, and trust-aligned AI agents. This guide bridges theory with practice for the modern AI practitioner.You Will:<ul><li>Discover reusable patterns such as reactors, planners, and tool-using agents that power effective autonomous systems.</li><li>Learn to build agents using Python with popular frameworks like LangChain and AutoGen, complete with reproducible GitHub code.</li><li>Dive into cutting-edge coordination mechanisms (e.g., MCP, A2A) that enable agents to collaborate and assign tasks dynamically.</li></ul>&nbsp;This book is for : Software Architects &amp; System Designers&nbsp;

Architecting Scalable, Ethical, and Trustworthy Systems for Enterprise

Agentic AI Systems in Practice

Mastering Sector and Industry Analysis

The Art of Financial Terrain

Anhand der Programmiersprache Python vermittelt dieses Buch die theoretischen und methodischen Grundlagen der Ökonometrie. Python ist bestens für AnfängerInnen geeignet und besitzt leistungsstarke Bibliotheken wie Pandas und Matplotlib, mit denen Datenbestände verwaltet bzw. bearbeitet und in Form aussagefähiger Grafiken dargestellt werden können. Mit der Bibliothek Statsmodels stehen effiziente Methoden für die Analyse und Auswertung von statistischen Daten als auch für die Regressionsanalyse zur Verfügung. LeserInnen benötigen keine fundierten Kenntnisse in der Programmierung, da die Kommandos in der Regel einen parametergesteuerten Zugriff auf die Methoden erlauben. Angesichts der Dominanz von Python in den Bereichen Data Science und KI ist die Wahl dieser Sprache eine zukunftssichere Entscheidung für die ökonometrische Analyse. Ergänzend zum Buch werden alle Python-Skripte und Datensätze auf SpringerLink zum Download bereitgestellt, um die direkte Umsetzung der Verfahren zu ermöglichen.Der Inhalt<ul><li>Die Grundlagen der Programmiersprache Python</li><li>Einführung in Pandas, NumPy und Matplotlib</li><li>Datenverarbeitung mit Pandas DataFrames</li><li>Datenvisualisierung mit Matplotlib</li><li>Deskriptive Statistik und statistische Grundlagen</li><li>Regressionsanalyse von Querschnittsdaten</li><li>Spezifikationstests und Modellvalidierung</li><li>Dynamische Regressionsmodelle für Zeitreihen</li><li>Regressionsanalyse von Paneldaten</li><li>Matrixbearbeitung mit Python</li><li>Kompakte Regressionsanalyse mittels Matrixalgebra</li></ul>Der AutorJürgen Malitte
 war beruflich in der IT- und Methodenberatung von Unternehmen sowie als Organisationsprogrammierer tätig und unterrichtet Mathematik/Statistik und Programmiersprachen in verschiedenen Bildungseinrichtungen.

Anhand der Programmiersprache Python vermittelt dieses Buch die theoretischen und methodischen Grundlagen der Ökonometrie. Python ist bestens für AnfängerInnen geeignet und besitzt leistungsstarke Bibliotheken wie Pandas und Matplotlib, mit denen Datenbestände verwaltet bzw. bearbeitet und in Form aussagefähiger Grafiken dargestellt werden können. Mit der Bibliothek Statsmodels stehen effiziente Methoden für die Analyse und Auswertung von statistischen Daten als auch für die Regressionsanalyse zur Verfügung. LeserInnen benötigen keine fundierten Kenntnisse in der Programmierung, da die Kommandos in der Regel einen parametergesteuerten Zugriff auf die Methoden erlauben. Angesichts der Dominanz von Python in den Bereichen Data Science und KI ist die Wahl dieser Sprache eine zukunftssichere Entscheidung für die ökonometrische Analyse. Ergänzend zum Buch werden alle Python-Skripte und Datensätze auf SpringerLink zum Download bereitgestellt, um die direkte Umsetzung der Verfahren zu ermöglichen.

Eine Einführung mit praktischen softwaregestützten Beispielen

Ökonometrie verstehen und anwenden mit Python

DK Complete Courses

Learning to code has never been easier than with this innovative visual guide to computer programming for beginners. In our digital world, coding skills are in high demand and the need for programmers is still growing. Taking the first steps in learning to code may seem daunting but by using a graphic method to break code into small chunks, this book brings essential skills easily within reach. Each chapter explores one of the most popular languages, with practical programming projects to show you how programming works. You'll learn to think like a programmer by breaking a problem down into parts, before turning those parts into lines of code. Short, easy-to-follow steps then show you, piece by piece, how to build a complete program. There are challenges for you to tackle to build your confidence before moving on. Written by a team of expert coders and coding teachers, the Beginner's Step-by-Step Coding Course is the ideal way to get to grips with coding.

Learn Computer Programming the Easy Way

Beginner's Step-by-Step Coding Course

A forward-looking primer on how AI models and systems work, the attacks that can disrupt them, and what security measures the industry uses to keep them safe. Artificial intelligence now underpins everything from chatbots to national infrastructure, but with new capability comes new risk. Attacks like prompt injection, data poisoning, and model theft are already targeting the systems we rely on. Practical AI Security is a comprehensive foundation to the field—a 0-to-60 guide to everything you need to know at the intersection of AI and cybersecurity. Drawing real-world experience securing deployed systems, Harriet Farlow demystifies how modern AI works, why it’s vulnerable, and how to protect it. You’ll learn how AI systems differ from machine learning models, why that matters for security, and how to defend both. Through clear explanations, real-world examples, and over 30 hands-on Python demos, you will: <ul><li>Understand how different kinds of machine learning models—from computer vision and language models to signal models—are built and how their architectures create unique vulnerabilities</li><li>Explore how these models are integrated into more autonomous, agentic AI systems, and why deployment introduces new weaknesses and risks</li><li>Identify, exploit, and defend against dozens of weaknesses and attacks across the AI lifecycle, including data poisoning, model theft, and prompt injection</li><li>Use industry frameworks such as OWASP and MITRE ATLAS to threat model different types of AI systems</li><li>Design and execute AI-specific red teaming campaigns, and understand what makes them distinct from traditional security tests</li><li>Examine how AI itself can be weaponized in cybersecurity, including cases where AI attacks other AI</li><li>Build robust frameworks for AI risk management, assurance, and testing</li><li>Bridge technical and policy perspectives to strengthen AI security culture across organizations</li></ul> Covering fundamentals through to advanced topics—from adversarial machine learning and red teaming to risk management, governance, and AI safety—this book turns theory into skill. Even if you don’t think you’re technical now, you’ll finish with practical confidence and a security mindset. Whether you use, build, deploy, or oversee AI, this isn’t niche knowledge—it’s the foundation for defending the technologies that will define the next era of human progress.

Break AI Systems. Then Secure Them. If you’re a security practitioner learning to operate in AI environments, or an ML engineer who needs to understand what adversaries actually do, Practical AI Security gives you the technical foundation the field demands. Built from first principles, this book takes you from how models fail to how they’re exploited to how they’re defended and audited. Every technique includes clear explanations and real-world examples, and you can run the attacks and defenses yourself with over 30 hands-on Python demos. <ul><li>Understand how different kinds of machine learning models create unique vulnerabilities, and explore how these models are integrated into more autonomous, agentic AI systems to introduce new weaknesses and risks.</li><li>Identify, exploit, and defend against dozens of weaknesses and attacks across the AI life cycle, including data poisoning, model theft, and prompt injection.</li><li>Evaluate AI systems for safety failures, bias, and alignment risks using structured benchmarking.</li><li>Threat-model agentic systems, RAG pipelines, and multimodal architectures using MITRE ATLAS, OWASP, and the MAESTRO framework.</li><li>Design and execute AI-specific red teaming campaigns, and understand what makes them distinct from traditional security tests.</li><li>Conduct rapid risk audits and navigate AI governance frameworks for real deployments.</li></ul> Whether you use, build, deploy, or oversee AI, this isn’t niche knowledge—it’s the foundation for defending the technologies that will define the next era of human progress.

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

Practical AI Security

Forecasting

Weitere Titel zum Thema