We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| eth-sri/fedavg_leakage | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| aggregate_batch_metrics | Ran | eth-sri/fedavg_leakage/fedavg/train_fed.py code served (permissive licence) · get_code("7a8d40473bad4f08") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recent attacks have shown that user data can be recovered from FedSGD updates, thus breaking privacy. However, these attacks are of limited practical relevance as federated learning typically uses the FedAvg algorithm. Compared to FedSGD, recovering data from FedAvg updates is much harder as: (i) the updates are computed at unobserved intermediate network weights, (ii) a large number of batches are used, and (iii) labels and network weights vary simultaneously across client steps. In this work, we propose a new optimization-based attack which successfully attacks FedAvg by addressing the above challenges. First, we solve the optimization problem using automatic differentiation that forces a simulation of the client's update that generates the unobserved parameters for the recovered labels and inputs to match the received client update. Second, we address the large number of batches by relating images from different epochs with a permutation invariant prior. Third, we recover the labels by estimating the parameters of existing FedSGD attacks at every FedAvg step. On the popular FEMNIST dataset, we demonstrate that on average we successfully recover >45% of the client's images from realistic FedAvg updates computed on 10 local epochs of 10 batches each with 5 images, compared to only <10% using the baseline. Our findings show many real-world federated learning implementations based on FedAvg are vulnerable.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2206.12395")
get_code_for_paper("2206.12395")
have("2206.12395")
Connect an agent — have() is free.