Jailbreaking LLMs : Protecting the Future of Enterprise Security / by Priyanka Neelakrishnan.

Format:

Book

Author/Creator:

Neelakrishnan, Priyanka.

Series:

Professional and Applied Computing Series

Language:

English

Subjects (All):

Data protection.

Artificial intelligence.

Data and Information Security.

Artificial Intelligence.

Local Subjects:

Data and Information Security.

Artificial Intelligence.

Physical Description:

1 online resource (592 pages)

Edition:

1st ed. 2026.

Place of Publication:

Berkeley, CA : Apress : Imprint: Apress, 2026.

Summary:

Large Language Models (LLMs) are rapidly transforming how enterprises operate, powering customer support, internal assistants, automated workflows, search, analytics, and decision-making systems. But as organizations adopt AI at scale, they are also introducing a new and expanding attack surface. Jailbreaking LLMs explores how attackers manipulate AI systems through prompt injection, jailbreaks, adversarial inputs, data poisoning, context manipulation, retrieval attacks, and unsafe tool usage to bypass safeguards, leak sensitive data, and influence AI behavior in unexpected ways. This book provides a practical guide to understanding, testing, and defending enterprise AI systems in the real world. Through real attack scenarios, security frameworks, red-teaming methodologies, governance strategies, and defensive architecture patterns, readers will learn how to build secure, resilient, and enterprise-ready LLM deployments. Covering everything from RAG security and agentic systems to incident response, AI governance, runtime monitoring, and future attack trends, this book connects AI innovation with modern cybersecurity practices. What you will learn Understand how LLM jailbreaks, prompt injection, and adversarial attacks work Identify vulnerabilities across enterprise AI systems, RAG pipelines, agents, and APIs Design and deploy secure, enterprise-ready LLM architectures Implement monitoring, logging, detection, and incident response workflows for AI systems Apply red-teaming and defensive testing strategies to evaluate LLM security Build governance, compliance, and ethical AI controls into enterprise deployments Understand emerging AI attack trends and future cybersecurity risks .

Contents:

Chapter 1. Jailbreaking LLMs and Its Security Implications

Chapter 2. LLM Security Infrastructure

Chapter 3: Designing and Deploying LLMs for Enterprise Use

Chapter 4. Security Vulnerabilities and Design Flaws in LLMs

Chapter 5. Exploitation of Security Vulnerabilities in LLMs

Chapter 6: Strategies for Safeguarding Jailbreak Attempts

Chapter 7. The Role of Red Teaming in LLM Security

Chapter 8. Responding to Jailbreaking in Enterprise LLMs

Chapter 9. Ethics and AI Governance in Enterprise Security

Chapter 10. LLMs and the Future of Cybersecurity

Optional Appendix A: World of LLMs

Optional Appendix B: Architecture of LLMs.

Notes:

Print version record.

ISBN:

9798868829581