# federated-learning

11 artikelengetagd met “federated-learning”

Poisoning bij federated learning

Attacking federated learning systems by submitting poisoned gradient updates from compromised participants while evading Byzantine-robust aggregation.

data-trainingfederated-learningpoisoningdistributed

Gevorderd

Aanvallen op federated learning

Attacking federated learning through model update poisoning, gradient leakage, free-rider attacks, and Byzantine fault exploitation.

federated-learninggradient-leakagemodel-poisoningbyzantinefree-rider

Gevorderd

Federated Learning Modelvergiftiging

Vergiftiging van federated learning-aggregatie via kwaadaardige gradient-updates en byzantijnse aanvalsvectoren.

frontierfederated-learningpoisoning

Expert

Federated Learning Security

Beveiligingsaanvallen op federated-learning-systemen, waaronder modelvergiftiging, data-inferentie en exploitatie van Byzantijnse fouten.

infrastructurefederated-learningmodel-poisoningprivacy

Gevorderd

Lab: poisoning-aanvallen op federated learning

Execute model poisoning attacks in a federated learning simulation by manipulating local model updates.

labsfederated-learningpoisoningadvanced

Gevorderd

Lab: poisoning-aanval op federated learning

Hands-on lab for understanding and simulating poisoning attacks against federated learning systems, where a malicious participant corrupts the shared model through crafted gradient updates.

labfederated-learningpoisoningexperthands-on

Expert

Poisoning-aanval op federated learning

Execute model poisoning attacks in a federated learning setting through adversarial participant manipulation.

labsfederated-learningpoisoningexpert

Expert

Vergiftiging van federated learning (training pipeline)

Architecturale kwetsbaarheden van federated learning: Byzantijnse aanvallen, modelvervanging, gradiëntmanipulatie en technieken om globale modellen te vergiftigen via kwaadwillende deelnemers.

federated-learningbyzantinemodel-replacementgradient-poisoningaggregationprivacy

Expert

Geavanceerde aanvalsvectoren voor training

Geavanceerde trainingsaanvallen: vergiftiging van federated learning, exploits van model merging, kwetsbaarheden in distributed training, risico's van emergente capaciteiten en aanvallen op synthetische-datapipelines.

advancedfederated-learningmodel-mergingdistributed-trainingemergencesynthetic-datatraining-security

Expert

Lab: Federated learning aanvallen

Praktisch lab dat modelvergiftigingsaanvallen implementeert in een gesimuleerde federated learning-opzet met het Flower-framework: Byzantijnse aanvallen, modelvervanging en het meten van aanvalsimpact.

labfederated-learninghands-onflowerbyzantinemodel-poisoningsimulation

Gevorderd

Aanvallen op Federated Learning (Training Pipeline)

Aanvallen op federated learning-opstellingen, waaronder modelvergiftiging, data-inferentie en manipulatie van aggregatie.

training-pipelinefederated-learningattacksdistributed

Expert