Doniyorkhon Obidov
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling
According to the abstract, Obidov, Yu, Guo and Yang introduce AttentionSwitch, a jailbreak defense that learns which attention heads in a frozen language model to adjust and by how much, claiming to be first to optimize both choices jointly.