References & Quick Reference

Comprehensive collection of cheat sheets, quick references, catalogs, checklists, and comparison matrices for AI red teaming, covering attack techniques, defense bypasses, tools, frameworks, and compliance.

This section serves as the practitioner's toolkit -- a collection of condensed references designed for quick access during active work. While the curriculum sections provide deep explanations and learning context, these references provide the distilled, actionable information you need when you are in the middle of an engagement and need to quickly look up an attack technique, find the right tool flag, or map a finding to a compliance framework.

Every reference in this collection is designed to be immediately useful. Cheat sheets compress entire topic areas into scannable formats. Quick references provide the specific commands, payloads, and configurations you need without the surrounding educational context. Catalogs enumerate techniques systematically so you can verify coverage. Checklists ensure you do not miss steps in structured processes. Comparison matrices help you select the right tool for the job. These are the resources you bookmark, print, and keep open during engagements.

Reference Categories

The references are organized by purpose to help you find what you need quickly.

Attack references provide quick-access catalogs of attack techniques and payloads. The AI Red Teaming Cheat Sheet covers the full engagement lifecycle in condensed form. The Prompt Injection Quick Reference and Prompt Injection Cheat Sheet provide injection payloads organized by technique type. The Jailbreak Technique Catalog enumerates known jailbreak methods with example payloads. The Common Attack Payload Reference provides copy-paste-ready attack strings organized by target and objective. These references are most useful during the attack execution phase of an engagement.

Defense references document defense mechanisms and how to bypass them. The Defense Bypass Quick Reference maps common defenses to their known weaknesses and bypass techniques. The LLM Security Checklist provides a structured assessment checklist for evaluating the defensive posture of AI deployments. These references support both the assessment planning and reporting phases.

Tool references help you select and configure the right tools. The Red Team Tool Comparison Matrix evaluates tools across dimensions including attack coverage, automation capability, reporting, and integration. The detailed Tool Comparison provides deeper feature-by-feature analysis. These references are valuable during engagement planning and lab setup.

Framework and compliance references connect findings to established standards. The Framework Mapping Reference maps between OWASP, NIST, MITRE ATLAS, and other frameworks so findings can be reported in the client's preferred framework. The OWASP LLM Top 10 Quick Reference provides the standard checklist for LLM application security. The Regulatory Quick Reference covers compliance requirements across jurisdictions. The Cloud AI Security Cheat Sheet addresses cloud-specific security considerations. The AI Incident Response Checklist provides the step-by-step process for responding to AI security incidents.

Learning references support structured skill development. The Curated Learning Paths organize the curriculum into recommended sequences based on your role and goals. The Extended AI Security Glossary defines specialized terminology used throughout the field.

What You'll Find in This Section

• AI Red Teaming Cheat Sheet -- Condensed engagement lifecycle reference covering scoping, reconnaissance, threat modeling, attack execution, and reporting
• Prompt Injection Quick Reference -- Organized catalog of injection techniques with example payloads
• LLM Security Checklist -- Structured assessment checklist for evaluating AI system security
• Curated Learning Paths -- Recommended study sequences organized by role and experience level
• Defense Bypass Quick Reference -- Common defenses mapped to bypass techniques
• Framework Mapping Reference -- Cross-reference between OWASP, NIST, MITRE ATLAS, EU AI Act, and other frameworks
• Extended AI Security Glossary -- Comprehensive terminology definitions for AI security
• Red Team Tool Comparison Matrix -- Feature comparison of major AI red teaming tools
• Prompt Injection Cheat Sheet -- Copy-paste-ready injection payloads
• Jailbreak Technique Catalog -- Systematic enumeration of jailbreak methods
• OWASP LLM Top 10 Quick Reference -- Condensed OWASP checklist
• Red Team Tool Comparison -- Detailed tool feature analysis
• Cloud AI Security Cheat Sheet -- Cloud-platform-specific security reference
• Regulatory Quick Reference -- Compliance requirements across jurisdictions
• AI Incident Response Checklist -- Step-by-step incident response process
• Common Attack Payload Reference -- Ready-to-use attack payloads organized by technique

Prerequisites

References assume familiarity with the corresponding curriculum content. No specific prerequisites are required to browse, but you will get the most value if you have:

• Completed the relevant curriculum sections for the reference area you are using
• Active engagement or lab work that creates a need for quick-access information
• Familiarity with at least one AI red teaming tool from the Walkthroughs section