SPEAR:Exact Gradient Inversion of Batches in Federated Learning
Dimitrov, Dimitar I., Baader, Maximilian, Müller, Mark Niklas, Vechev, Martin
–arXiv.org Artificial Intelligence
Federated learning is a framework for collaborative machine learning where clients only share gradient updates and not their private data with a server. However, it was recently shown that gradient inversion attacks can reconstruct this data from the shared gradients. In the important honest-but-curious setting, existing attacks enable exact reconstruction only for a batch size of $b=1$, with larger batches permitting only approximate reconstruction. In this work, we propose SPEAR, the first algorithm reconstructing whole batches with $b >1$ exactly. SPEAR combines insights into the explicit low-rank structure of gradients with a sampling-based algorithm. Crucially, we leverage ReLU-induced gradient sparsity to precisely filter out large numbers of incorrect samples, making a final reconstruction step tractable. We provide an efficient GPU implementation for fully connected networks and show that it recovers high-dimensional ImageNet inputs in batches of up to $b \lesssim 25$ exactly while scaling to large networks. Finally, we show theoretically that much larger batches can be reconstructed with high probability given exponential time.
arXiv.org Artificial Intelligence
Jun-3-2024
- Country:
- Europe (0.28)
- North America
- Canada (0.14)
- United States (0.14)
- Genre:
- Research Report > New Finding (0.67)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology: