Argus detects backdoors in decentralized learning by local trigger analysis and neighbor similarity checks on consistency, with theoretical convergence guarantees and empirical reductions in attack success up to 90 points.
Machine learning with adversaries: Byzantine tolerant gradient descent
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning
Argus detects backdoors in decentralized learning by local trigger analysis and neighbor similarity checks on consistency, with theoretical convergence guarantees and empirical reductions in attack success up to 90 points.