К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
AI Security Fundamentals – LLM Threats & OWASP 2026 · LearnSpace
Назад в каталог
courseraПрограммирование

AI Security Fundamentals – LLM Threats & OWASP 2026

Курс от Packt
Средний≈ 12.8 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

This course features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. In this course, you’ll gain a comprehensive understanding of the security principles vital for securing Large Language Model (LLM) applications. You will explore critical vulnerabilities, such as prompt injection, data poisoning, and improper output handling, while learning strategies to mitigate these risks. Through engaging modules, you will analyze real-world examples of successful and unsuccessful LLM implementations, enabling you to understand the delicate balance between functionality and security in AI systems. The course is structured across 12 detailed modules, beginning with an introduction to LLM applications and their associated security challenges. As you progress, you will dive into specific topics such as prompt injection, sensitive information disclosure, and supply chain vulnerabilities, with each module providing practical, hands-on solutions to counter these risks. You’ll also explore essential topics such as the role of third-party models, data minimization, and model poisoning, which are key to securing AI applications at scale. Designed for security professionals and AI developers, this course provides you with the tools needed to address security issues within LLM systems proactively. You’ll walk away with the ability to implement best practices for securing LLM development and deployment processes. Whether you are working in AI development, security, or policy, this course will help you understand and address the security complexities that come with LLM technology. By the end of the course, you will be able to assess LLM vulnerabilities, apply security principles to mitigate risks, design secure LLM applications, and implement strategies to defend against prompt injections and other security threats.

Навыки, которые вы освоите

AI SecurityApplication SecurityLarge Language ModelingSecurity ControlsInformation PrivacySecure CodingData GovernancePersonally Identifiable InformationPrompt EngineeringLLM ApplicationAuthorization (Computing)Data ModelingSecurity TestingSupply Chain ManagementData Loss PreventionOpen Web Application Security Project (OWASP)

Программа курса

12 модулей · 97 учебных материалов

01Module 1: Introduction to LLM Application Security8 материалов

Module 1: Introduction to LLM Application Security

Introduction to LLMs and Their ApplicationsВидеоFull Course ResourcesЧтениеOverview of Security Challenges Specific to LLM ApplicationsВидеоIntroduction to the OWASP Top 10 LLM Applications ListВидео

Учитесь у экспертов

Packt - Course Instructors

Преподаватель курса

AI Security Fundamentals – LLM Threats & OWASP 2026
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 12.8 ч

12 модулей

Язык: Английский

Часть программы вашего университета
Importance of Secure LLM Development and DeploymentВидео
Real-World Case Studies of Successful/Unsuccessful LLM ImplementationsВидео
Common LLM Application Architectures (e.g., RAG)Видео
The Threat Landscape: Motivations of Attackers Targeting LLM ApplicationsВидео
02Module 2: LLM01:2025 – Prompt Injection9 материалов

Module 2: LLM01:2025 – Prompt Injection

Detailed Explanation of Prompt Injection VulnerabilitiesВидеоTypes of Prompt Injection (Direct and Indirect)ВидеоPotential Impacts of Prompt Injection AttacksВидеоPrevention and Mitigation StrategiesВидеоEvolution of Prompt Injection Techniques and Their Increasing SophisticationВидеоImpact Deep Dive: Specific ExamplesВидеоDefense-in-Depth: Combining Input Validation, Output Filtering, and Human ReviewВидеоUnderstanding and Defending Against Prompt Injection AttacksDIALOGUELLM01:2025 – Prompt Injection - AssessmentЗадание
03Module 3: LLM02:2025 – Sensitive Information Disclosure8 материалов

Module 3: LLM02:2025 – Sensitive Information Disclosure

Common Examples of Vulnerabilities (PII Leakage, Proprietary Algorithm Exposure)ВидеоUnderstanding the Risks of Sensitive Information Disclosure in LLM ApplicationsВидеоPrevention and Mitigation Strategies (Sanitization, Access Controls, etc.)ВидеоData Minimization: Importance of Minimizing Sensitive Data CollectionВидеоPrivacy-Enhancing Technologies – PETВидеоLegal and Compliance: Legal Implications of Sensitive Data DisclosureВидеоPreventing Sensitive Data Leaks in LLM AppsDIALOGUELLM02:2025 – Sensitive Information Disclosure - AssessmentЗадание
04Module 4: LLM03:2025 – Supply Chain8 материалов

Module 4: LLM03:2025 – Supply Chain

Supply Chain Vulnerabilities in LLM Development and DeploymentВидеоRisks Associated with Third-Party Models, Data, and ComponentsВидеоPrevention and Mitigation Strategies for Supply Chain RisksВидеоSBOMs in Detail: Explanation of Software Bill of Materials (SBOMs) and Their ImpactВидеоModel Provenance Challenges: Difficulties in Verifying the Origin and IntegrityВидеоGovernance and Policy: Importance of Clear Policies for Using Third-Party LLMsВидеоSecuring the LLM Supply Chain: Risks and MitigationDIALOGUELLM03:2025 – Supply Chain - AssessmentЗадание
05Module 5: LLM04:2025 – Data and Model Poisoning8 материалов

Module 5: LLM04:2025 – Data and Model Poisoning

Understanding Data and Model Poisoning AttacksВидеоHow Poisoning Can Impact LLM Behavior and SecurityВидеоPrevention and Mitigation StrategiesВидеоPoisoning Scenarios Across the Lifecycle: Poisoning in Training and Fine-TuningВидеоBackdoor Attacks: Detail on How Backdoors Are InsertedВидеоRobustness Testing: Need for Rigorous Testing to Detect Poisoning EffectsВидеоUnderstanding and Preventing Data Poisoning in Language ModelsDIALOGUELLM04:2025 – Data and Model Poisoning - AssessgmentЗадание
06Module 6: LLM05:2025 – Improper Output Handling7 материалов

Module 6: LLM05:2025 – Improper Output Handling

Risks Associated with Improper Handling of LLM OutputsВидеоVulnerabilities Such as XSS, SQL Injection, and Remote Code ExecutionВидеоPrevention and Mitigation StrategiesВидеоOutput Encoding Examples: Code Examples for Different Contexts (e.g., HTML, SQL)ВидеоReal-World Exploits: Detail Cases Where Improper Output Handling Led to BreachesВидеоSecuring LLM Output: Preventing Improper Output HandlingDIALOGUELLM05:2025 – Improper Output Handling - AssessmentЗадание
07Module 7: LLM06:2025 – Excessive Agency8 материалов

Module 7: LLM06:2025 – Excessive Agency

The Concept of Agency in LLM Systems and Associated RisksВидеоRisks of Excessive Functionality, Permissions, and AutonomyВидеоPrevention and Mitigation StrategiesВидеоAgentic Systems: Explanation of LLM Agents, Their Benefits, and RisksВидеоLeast Privilege in Depth: Detailed Guidance on Implementing Least PrivilegeВидеоAuthorization Frameworks: Best Practices for Managing Authorization in LLMВидеоDesigning Safe LLM Agents: Tools, Permissions, and AuthorizationDIALOGUELLM06:2025 – Excessive Agency - AssessmentЗадание
08Module 8: LLM07:2025 – System Prompt Leakage8 материалов

Module 8: LLM07:2025 – System Prompt Leakage

Vulnerability of System Prompt LeakageВидеоRisks Associated with Exposing System PromptsВидеоPrevention and Mitigation StrategiesВидеоPrompt Engineering Risks: How Prompt Engineering Can Extract System PromptsВидеоDefense in Depth for PromptsВидеоSecure Design PrinciplesВидеоUnderstanding and Preventing System Prompt Leakage in LLMsDIALOGUELLM07:2025 – System Prompt Leakage - AssessmentЗадание
09Module 9: LLM08:2025 – Vector and Embedding Weaknesses8 материалов

Module 9: LLM08:2025 – Vector and Embedding Weaknesses

Vulnerabilities Related to Vector and Embedding Usage in LLM ApplicationsВидеоRisks of Unauthorized Access, Data Leakage, and PoisoningВидеоPrevention and Mitigation StrategiesВидеоEmbedding Security: Details on Securing Vector Databases and EmbeddingsВидеоRAG Security Best PracticesВидеоEmerging ResearchВидеоSecuring Vector Embeddings in LM ApplicationsDIALOGUELLM08:2025 – Vector and Embedding Weaknesses - AssessmentЗадание
10Module 10: LLM09:2025 – Misinformation8 материалов

Module 10: LLM09:2025 – Misinformation

The Issue of Misinformation Generated by LLMsВидеоCauses and Potential Impacts of MisinformationВидеоPrevention and Mitigation StrategiesВидеоThe Spectrum of MisinformationВидеоImpact on Specific DomainsВидеоDetection and Mitigation TechniquesВидеоIdentifying and Mitigating Misinformation in LLM OutputsDIALOGUELLM09:2025 – Misinformation - AssessmentЗадание
11Module 11: LLM10:2025 – Unbounded Consumption8 материалов

Module 11: LLM10:2025 – Unbounded Consumption

Risks Associated with Excessive and Uncontrolled LLM UsageВидеоVulnerabilities That Can Lead to Denial of Service, Economic Losses, etc.ВидеоPrevention and Mitigation StrategiesВидеоEconomic Denial of ServiceВидеоRate Limiting StrategiesВидеоModel Extraction DefensesВидеоUnderstanding and Preventing Unbounded LLM ConsumptionDIALOGUELLM10:2025 – Unbounded Consumption - AssessmentЗадание
12Module 12: Best Practices and Future Trends in LLM Security9 материалов

Module 12: Best Practices and Future Trends in LLM Security

Summary of Key Security Principles for LLM ApplicationsВидеоEmerging Trends and Future Challenges in LLM SecurityВидеоResources and Further LearningВидеоSecure LLM Development Lifecycle: Integrating Security into Every StageВидеоEmerging TechnologiesВидеоThe Role of Standards and RegulationsВидеоBest Practices and Future Trends in LLM Security - AssessmentЗаданиеFull Course Practice AssessmentЗаданиеFull Course AssessmentЗадание