Decentralized SGD generalization error is bounded by O(init/(µNZ)) plus noise and heterogeneity terms, with a Byzantine-attack term that persists as sample size grows.
Sensitivity Curve Maximization: Attacking Robust Aggregators in Distributed Learning
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
In distributed learning agents aim at collaboratively solving a global learning problem. It becomes more and more likely that individual agents are malicious or faulty with an increasing size of the network. This leads to a degeneration or complete breakdown of the learning process. Classical aggregation schemes are prone to breakdown at small contamination rates, therefore robust aggregation schemes are sought for. While robust aggregation schemes can generally tolerate larger contamination rates, many have been shown to be susceptible to carefully crafted malicious attacks. In this work, we show how the sensitivity curve (SC), a classical tool from robust statistics, can be used to systematically derive optimal attack patterns against arbitrary robust aggregators, in most cases rendering them ineffective. We show the effectiveness of the proposed attack in multiple simulations.
citation-role summary
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Generalization Error Analysis for Attack-Free and Byzantine-Resilient Decentralized Learning with Data Heterogeneity
Decentralized SGD generalization error is bounded by O(init/(µNZ)) plus noise and heterogeneity terms, with a Byzantine-attack term that persists as sample size grows.