Research & Guides
Research, guides, and deep dives into AI security, prompt injection, and LLM red teaming.
A practical guide to AI jailbreak techniques: roleplay and DAN prompts, fake authority, encoding, multi-turn attacks, and reasoning exploits. Learn how each one works, why it bypasses safety, and how to defend.
How homoglyph attacks use look-alike Unicode characters to slip banned words past AI keyword filters, why the model still understands them, and how to detect and defend against them.
Zero-width and invisible Unicode characters can hide instructions from humans while LLMs still read them. Learn how unicode steganography works, how attackers use it against LLMs, and how to detect it.
Compare Lakera Gandalf, HackAPrompt, PortSwigger and 8 more prompt injection games and labs by format, price, real LLMs, levels, and best use case.
Prompt injection is listed as LLM01:2025 in the OWASP Top 10 for LLM Applications. Learn what it is, how it works, direct vs indirect types, real-world examples, and how to practice detecting it and analyzing mitigations for free.
A hands-on guide to 10 prompt injection techniques: ignore previous instructions, role-play attacks, encoding tricks, multilingual bypasses, RAG poisoning, and more - with example payloads.
Prompt injection and jailbreaking are often confused. Learn the key differences in goals, targets, techniques, and severity - and why OWASP treats them differently.
A guide to defending against prompt injection: how each attack category works, how to test evasions with a live encoder, and how to harden your LLM app. Links to the full interactive cheat sheet.
A step-by-step guide to learning AI security and LLM red teaming. Covers essential skills, free resources, hands-on labs, and career paths in AI security.
AI red teaming explained: what it is, why organizations need it, common methodologies, and how to start practicing with real LLMs in a safe environment.