FLock claims the first secure decentralized fine-tuning of a 70B-class LLM, but the experiments omit the validator mechanism and compare against weak baselines.
Defending against poisoning attacks in federated learning with blockchain
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Scaling Decentralized Learning with FLock
FLock claims the first secure decentralized fine-tuning of a 70B-class LLM, but the experiments omit the validator mechanism and compare against weak baselines.