NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#byzantine-attack

0 stories this week · 1 this month · 1 in 6 months · mostly security

Stories per day · 30 days

Relatedfederated-learning1 hypergraph1 llama1 llm1 model-poisoning1 qwen1

1 stories, newest first · one card per story

arXiv cs.CR26d ago

Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing

HMP-GAE filters Byzantine updates during federated training of Qwen-2.5 and Llama-3.2.

federated-learning byzantine-attack

2