Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated Learning
New gradient inversion attacks tied to erasure-coding theory recover 94–100% of ImageNet batches, showing federated learning privacy leakage is underestimated.
1 stories, newest first · one card per story
New gradient inversion attacks tied to erasure-coding theory recover 94–100% of ImageNet batches, showing federated learning privacy leakage is underestimated.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views