AttentionSwitch2 min read
AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling
Large language models have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to jailbreak attacks that circumvent safety mechanisms and elicit harmful or unintended outputs.
By Doniyorkhon Obidov, Honggang Yu, Xiaolong Guo, Kaichen YangarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Nov 9, 2026.
Comments
Sign in to join the discussion.