Skip to content
conftrace_

self-attention analysis

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (1) exhaustive search (1) gradient inversion attack (1) gradient inversion (1) exact reconstruction (1) token recovery (1) text reconstruction (1) privacy attack (1) federated learning (1)

Papers

DAGER: Exact Gradient Inversion for Large Language Models NeurIPS 2024