arXiv Artificial Intelligence

Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning

2 hours ago 10.08.2026 07:00 👁 1 views
Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning

Quick summary

arXiv:2608.06637v1 Announce Type: cross Abstract: Robust aggregation methods are widely used in federated learning to mitigate the impact of adversarial client behavior. Distance-based aggregation rules, such as Krum and Multi-Krum, select updates that are closest to the majority under the assumption that benign updates form a compact cluster. However, these methods rely on geometric properties that can be exploited by adaptive adversaries. We introduce the Krum-Proxy attack, a selection-aware backdoor injection strategy that consistently bypasses Byzantine-robust aggregation. Rather than rely

Key takeaways

  • arXiv:2608.06637v1 Announce Type: cross Abstract: Robust aggregation methods are widely used in federated learning to mitigate the impact of adversarial client behavior.
  • Distance-based aggregation rules, such as Krum and Multi-Krum, select updates that are closest to the majority under the assumption that benign updates form a compact cluster.
  • However, these methods rely on geometric properties that can be exploited by adaptive adversaries.

Why it matters

“Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning” illustrates how changes in the AI ecosystem can affect products, workflows and user expectations together. Its lasting significance depends on measurable adoption, cost and safety outcomes.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗