A hybrid sparse Byzantine attack using network pruning insights and slow accumulation bypasses eight state-of-the-art defenses in federated learning simulations.
Long-short history of gradients is all you need: Detecting malicious and unreliable clients in federated learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning
A hybrid sparse Byzantine attack using network pruning insights and slow accumulation bypasses eight state-of-the-art defenses in federated learning simulations.