Courses & Learning

Modular red teaming course framework for structured LLM security evaluation.

Framework for learning LLM vulnerability testing through hands-on attack scenarios.

Benchmark framework for analyzing and comparing adversarial jailbreak methods systematically.

Prompt injection detection benchmark for evaluating and comparing defense effectiveness.

AI risk taxonomy and benchmark framework for systematic safety evaluation.

Framework for learning adversarial refinement techniques against LLM safety measures.

Educational resource on secure code anti-patterns and security context for AI applications.

AI-assisted security workflow library teaching offensive and defensive collaboration patterns.

Library of detection functions for learning LLM output monitoring and anomaly detection.

Semgrep rules for detecting data leaks in Prisma, Django, and Entity Framework ORMs.