XFED is the first aggregation-agnostic non-collusive model poisoning attack that bypasses eight state-of-the-art defenses on six benchmark datasets without attacker coordination.
Cross-silo feder- ated learning: Challenges and opportunities
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
The work provides the first formal definitions of Rashomon sets for federated learning and introduces a multiplicity-aware training pipeline evaluated on standard benchmarks.
FMTC learns personalized clustering models on clients and uses server-side tensor low-rank regularization to capture shared structure across heterogeneous clients in a privacy-preserving federated setting.
citing papers explorer
-
XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers
XFED is the first aggregation-agnostic non-collusive model poisoning attack that bypasses eight state-of-the-art defenses on six benchmark datasets without attacker coordination.
-
Rashomon Sets and Model Multiplicity in Federated Learning
The work provides the first formal definitions of Rashomon sets for federated learning and introduces a multiplicity-aware training pipeline evaluated on standard benchmarks.
-
Federated Multi-Task Clustering
FMTC learns personalized clustering models on clients and uses server-side tensor low-rank regularization to capture shared structure across heterogeneous clients in a privacy-preserving federated setting.