- An understanding of large language models and prompt-based interfaces
- Experience building LLM applications using Python
- Familiarity with API integrations and cloud-based deployments
Audience
- AI developers
- Application and solution architects
- Technical product managers working with LLM tools
LLM application security is the discipline of designing, building, and maintaining safe, trustworthy, and policy-compliant systems using large language models.
This instructor-led, live training (online or onsite) is aimed at intermediate-level to advanced-level AI developers, architects, and product managers who wish to identify and mitigate risks associated with LLM-powered applications, including prompt injection, data leakage, and unfiltered output, while incorporating security controls like input validation, human-in-the-loop oversight, and output guardrails.
By the end of this training, participants will be able to:
- Understand the core vulnerabilities of LLM-based systems.
- Apply secure design principles to LLM app architecture.
- Use tools such as Guardrails AI and LangChain for validation, filtering, and safety.
- Integrate techniques like sandboxing, red teaming, and human-in-the-loop review into production-grade pipelines.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
Overview of LLM Architecture and Attack Surface
- How LLMs are built, deployed, and accessed via APIs
- Key components in LLM app stacks (e.g., prompts, agents, memory, APIs)
- Where and how security issues arise in real-world use
Prompt Injection and Jailbreak Attacks
- What is prompt injection and why it’s dangerous
- Direct and indirect prompt injection scenarios
- Jailbreaking techniques to bypass safety filters
- Detection and mitigation strategies
Data Leakage and Privacy Risks
- Accidental data exposure through responses
- PII leaks and model memory misuse
- Designing privacy-conscious prompts and retrieval-augmented generation (RAG)
LLM Output Filtering and Guarding
- Using Guardrails AI for content filtering and validation
- Defining output schemas and constraints
- Monitoring and logging unsafe outputs
Human-in-the-Loop and Workflow Approaches
- Where and when to introduce human oversight
- Approval queues, scoring thresholds, fallback handling
- Trust calibration and role of explainability
Secure LLM App Design Patterns
- Least privilege and sandboxing for API calls and agents
- Rate limiting, throttling, and abuse detection
- Robust chaining with LangChain and prompt isolation
Compliance, Logging, and Governance
- Ensuring auditability of LLM outputs
- Maintaining traceability and prompt/version control
- Aligning with internal security policies and regulatory needs
Summary and Next Steps
United Arab Emirates - Building Secure and Responsible LLM Applications
Qatar - Building Secure and Responsible LLM Applications
Egypt - Building Secure and Responsible LLM Applications
Saudi Arabia - Building Secure and Responsible LLM Applications
South Africa - Building Secure and Responsible LLM Applications
Brasil - Building Secure and Responsible LLM Applications
Canada - Building Secure and Responsible LLM Applications
中国 - Building Secure and Responsible LLM Applications
香港 - Building Secure and Responsible LLM Applications
澳門 - Building Secure and Responsible LLM Applications
台灣 - Building Secure and Responsible LLM Applications
USA - Building Secure and Responsible LLM Applications
Österreich - Building Secure and Responsible LLM Applications
Schweiz - Building Secure and Responsible LLM Applications
Deutschland - Building Secure and Responsible LLM Applications
Czech Republic - Building Secure and Responsible LLM Applications
Denmark - Building Secure and Responsible LLM Applications
Estonia - Building Secure and Responsible LLM Applications
Finland - Building Secure and Responsible LLM Applications
Greece - Building Secure and Responsible LLM Applications
Magyarország - Building Secure and Responsible LLM Applications
Ireland - Building Secure and Responsible LLM Applications
Luxembourg - Building Secure and Responsible LLM Applications
Latvia - Building Secure and Responsible LLM Applications
España - Building Secure and Responsible LLM Applications
Italia - Building Secure and Responsible LLM Applications
Lithuania - Building Secure and Responsible LLM Applications
Nederland - Building Secure and Responsible LLM Applications
Norway - Building Secure and Responsible LLM Applications
Portugal - Building Secure and Responsible LLM Applications
România - Building Secure and Responsible LLM Applications
Sverige - Building Secure and Responsible LLM Applications
Türkiye - Building Secure and Responsible LLM Applications
Malta - Building Secure and Responsible LLM Applications
Belgique - Building Secure and Responsible LLM Applications
France - Building Secure and Responsible LLM Applications
日本 - Building Secure and Responsible LLM Applications
Australia - Building Secure and Responsible LLM Applications
Malaysia - Building Secure and Responsible LLM Applications
New Zealand - Building Secure and Responsible LLM Applications
Philippines - Building Secure and Responsible LLM Applications
Singapore - Building Secure and Responsible LLM Applications
Thailand - Building Secure and Responsible LLM Applications
Vietnam - Building Secure and Responsible LLM Applications
India - Building Secure and Responsible LLM Applications
Argentina - Building Secure and Responsible LLM Applications
Chile - Building Secure and Responsible LLM Applications
Costa Rica - Building Secure and Responsible LLM Applications
Ecuador - Building Secure and Responsible LLM Applications
Guatemala - Building Secure and Responsible LLM Applications
Colombia - Building Secure and Responsible LLM Applications
México - Building Secure and Responsible LLM Applications
Panama - Building Secure and Responsible LLM Applications
Peru - Building Secure and Responsible LLM Applications
Uruguay - Building Secure and Responsible LLM Applications
Venezuela - Building Secure and Responsible LLM Applications
Polska - Building Secure and Responsible LLM Applications
United Kingdom - Building Secure and Responsible LLM Applications
South Korea - Building Secure and Responsible LLM Applications
Pakistan - Building Secure and Responsible LLM Applications
Sri Lanka - Building Secure and Responsible LLM Applications
Bulgaria - Building Secure and Responsible LLM Applications
Bolivia - Building Secure and Responsible LLM Applications
Indonesia - Building Secure and Responsible LLM Applications
Kazakhstan - Building Secure and Responsible LLM Applications
Moldova - Building Secure and Responsible LLM Applications
Morocco - Building Secure and Responsible LLM Applications
Tunisia - Building Secure and Responsible LLM Applications
Kuwait - Building Secure and Responsible LLM Applications
Oman - Building Secure and Responsible LLM Applications
Slovakia - Building Secure and Responsible LLM Applications
Kenya - Building Secure and Responsible LLM Applications
Nigeria - Building Secure and Responsible LLM Applications
Botswana - Building Secure and Responsible LLM Applications
Slovenia - Building Secure and Responsible LLM Applications
Croatia - Building Secure and Responsible LLM Applications
Serbia - Building Secure and Responsible LLM Applications
Bhutan - Building Secure and Responsible LLM Applications
Nepal - Building Secure and Responsible LLM Applications
Uzbekistan - Building Secure and Responsible LLM Applications