Give a taxonomy of LLM jailbreaks and the layered defenses that actually hold up.

Roleplay, obfuscation, optimization-based suffixes, and multi-turn escalation are different attack classes that need different defenses. The signal is organizing the space and pairing each class with a control instead of hoping one filter covers all.

Updated Aug 2026 · Grounded in real Applied AI Engineer interview loops and written to a senior-engineer editorial bar.