Taxonomy
-
Prompt Injection vs Jailbreak: Two Different Attacks on LLMs
Prompt injection and jailbreak get conflated constantly, but they hit different layers and need different defenses. Here is how to tell them apart.
-
Crescendo Multi-Turn Jailbreaks: Why Defenses Miss Them
Crescendo multi-turn jailbreaks evade per-message defenses by exploiting conversation context, requiring session-level classification and monitoring.
-
LLM Jailbreak Taxonomy 2026: How the Techniques Cluster
Six years of jailbreak research has produced a messy literature. This taxonomy organizes working techniques by the behavioral property each one exploits.