federated-decentralization-tensions-with-data-integrity

IN derived (depth 1)

Created 2026-06-21T14:12:26+00:00 · Reviewed 2026-06-21T15:37:01+00:00

Federated learning's privacy-preserving decentralization creates a structural tension with data integrity — distributing training across user devices prevents central data inspection, making federated systems inherently more vulnerable to data poisoning attacks than centralized training, as malicious data injections cannot be detected or filtered by a central authority that never sees the raw data.

Justifications

SL — Decentralized training that preserves privacy by hiding raw data also hides poisoned data

Antecedents (all must be IN):

IN ml-federated-learning-decentralized — Federated learning decentralizes training across user devices, preserving privacy by not sending raw data to a central server (e.g., Google Gboard)
IN dl-data-poisoning-corrupts-training-data — Data poisoning is an adversarial attack where false data is injected into training sets to degrade model performance.