Building Secure and Responsible LLM Applications Training Course

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