Skip to content
Sagan

Paper

Scalable Hierarchical Attention Transformers for Multi-Turn Jailbreak Detection in Long Conversations

Unreadunread

AI summary

arXiv:2606. 21082v1 Announce Type: new Abstract: Multi-turn jailbreaks can evade turn-level moderation by spreading unsafe intent across a dialogue through gradual escalation, reframing, and role manipulation.