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 prompt injection is and why it poses a significant danger.
• Direct and indirect prompt injection scenarios.
• Jailbreaking techniques used to bypass safety filters.
• Detection and mitigation strategies.

Data Leakage and Privacy Risks

• Accidental data exposure through model responses.
• PII leaks and misuse of model memory.
• Designing privacy-conscious prompts and retrieval-augmented generation (RAG).

LLM Output Filtering and Guarding

• Utilizing Guardrails AI for content filtering and validation.
• Defining output schemas and constraints.
• Monitoring and logging unsafe outputs.

Human-in-the-Loop and Workflow Approaches

• Identifying where and when to introduce human oversight.
• Approval queues, scoring thresholds, and fallback handling.
• Trust calibration and the role of explainability.

Secure LLM App Design Patterns

• Implementing 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 the auditability of LLM outputs.
• Maintaining traceability and prompt/version control.
• Aligning with internal security policies and regulatory requirements.

Summary and Next Steps