Introduction to Machine Learning with Security

این کتاب یک راهنمای جامع در زمینه کاربردهای یادگیری ماشین در مهندسی امنیت سایبری است. در این اثر، مفاهیم کلیدی و پیشرفته یادگیری ماشین از جمله پیش‌پردازش داده‌ها، انتخاب مدل‌های بهینه، تنظیم هایپرپارامترها و ارزیابی عملکرد الگوریتم‌ها، با تمرکز بر کاربردهای امنیتی مورد بررسی قرار می‌گیرد. مباحث کتاب شامل تشخیص تهدیدات، شناسایی نفوذ، تحلیل الگوهای رفتاری غیرمعمول و کشف حملات پیچیده است. همچنین، چالش‌های عملی در استقرار سیستم‌های امنیتی مبتنی بر یادگیری ماشین تحلیل شده و بهترین روش‌ها، معماری‌های مقاوم و استراتژی‌های دفاعی پیشرفته برای مقابله با تهدیدات نوظهور ارائه می‌شود.

این کتاب برای مهندسان امنیت، متخصصان سایبری، دانشمندان داده و پژوهشگران علاقمند به ترکیب یادگیری ماشین با امنیت سایبری توصیه می‌شود. همچنین، دانشجویان و علاقه‌مندان به حوزه‌های فناوری اطلاعات که به دنبال بهره‌مندی از تکنیک‌های نوین در توسعه سیستم‌های امنیتی هستند، از مطالب ارائه شده در این کتاب بهره‌مند خواهند شد.

This book provides an introduction to machine learning and cloud computing, both from conceptual and practical levels, along with their usage with a Public Cloud infrastructure. The authors emphasize fundamentals and best practices for using AI and ML in a dynamic infrastructure with cloud computing and security considerations, preparing readers to select and make use of appropriate techniques. Important topics are demonstrated using real applications and several case studies.

In addition, this book:

• Provides broad coverage of AI, Machine Learning and Cloud Computing;
• Uses real examples and case studies to demonstrate key topics;
• Demonstrates concepts, as well as practical usage.

Table of Contents

Part I- Theory

1. Machine Learning Concepts  

2. Machine Learning Algorithms  

3. Deep Learning and Cloud Computing  

4. Cloud Computing Concepts  

5. Information Security and Cloud Computing  

6. Trust and Security in a Cloud Environment  

7. Hardware Based AI and ML  

8. Hardware Based Security  

Part II- Practices

9. Practical Aspects in Machine Learning  

10. Analytics in the Cloud  

11. Healthcare in the Cloud: A Few Case Studies  

12. Evolution and Risks of LLMs  

13. Machine Learning Operations

About the Author

Pramod Gupta has more than 20 years of experience as a researcher and academician in various organizations including work with NASA, GE, VISA, and University of California and startups. He has a PhD from McMaster University in Electrical and Computer Engineering with specialization in Neuro-Control of Robotic Manipulators. He has more than 40 publications on these subjects. His research areas include Neural Networks, Machine Learning, Artificial Intelligence, Data Modeling and Analytics and Data mining. Presently, he is an Adjunct Faculty and working as an independent data science consultant.

Naresh K. Sehgal is a CTO at the Deeply Human AI. Before that he worked at NovaSignal for 3 years and at Intel for 31 years in various Engineering and Management roles. Naresh has earned his B.E. from Punjab Engineering College, M.S. and Ph.D. from Syracuse University. He also taught a Cloud Computing class at Santa Clara University, where he earned an MBA.

John M. Acken is a research faculty member in the Electrical and Computer Engineering Department, Portland State University, Portland, OR. John received his BS and MS in Electrical Engineering from Oklahoma State University and Ph. D. in Electrical Engineering from Stanford University. His projects include technology and devices for information security and identity authentication. John has worked as an Electrical Engineer and Manager at several companies, including the US Army, Sandia National Labs in Albuquerque, New Mexico and Intel in Santa Clara, CA. John’s time in the US Army was in the Army Security Agency, a branch of NSA during the Vietnam War.