AI security fundamentals : LLM threats and OWASP principles 2026.

Format:

Video

Author/Creator:

Nednur, Anand Rao, author.

Contributor:

Packt Publishing, publisher.

Language:

English

Subjects (All):

Computer networks--Security measures.

Computer networks.

Natural language processing (Computer science).

Artificial intelligence.

Physical Description:

1 online resource (1 video file (06 hr., 10 min.)) : sound, color.

Edition:

[First edition].

Place of Publication:

[Birmingham, United Kingdom] : Packt Publishing, 2025.

Summary:

In this 6-hour course, you will gain a comprehensive understanding of security challenges specific to Large Language Models (LLMs) and learn strategies to protect them from various threats, including prompt injection and sensitive information disclosure. The course covers preventive measures, regulatory compliance, and evolving risks like misinformation generation, ensuring a solid foundation for securing AI systems. What I will be able to do after this course Understand the core security challenges faced by LLM applications Learn how to defend against prompt injection vulnerabilities and attacks Explore strategies for preventing sensitive information disclosure in LLMs Gain insights into securing LLM supply chains and third-party dependencies Learn techniques for detecting and mitigating data and model poisoning attacks Course Instructor(s) Anand Rao Nednur is a cybersecurity and cloud expert with over 20 years of experience. He holds various certifications and has helped numerous organizations optimize their cloud infrastructure. Anand shares his knowledge through blogs and YouTube videos, making complex topics accessible to learners. Who is it for? This course is designed for technical professionals in AI, machine learning, and cybersecurity, including developers, security engineers, and data scientists. It's ideal for those with a basic understanding of AI or cybersecurity, especially those working with LLM systems or AI applications requiring robust security frameworks.

Notes:

OCLC-licensed vendor bibliographic record.

ISBN:

1-80638-119-2

OCLC:

1553676480