Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The Shift Toward Open and Reproducible AI Research," Under Review, 2026. doi: 10.48550/arXiv.2606.16974..
TabLeak: Tabular Data Leakage in Federated Learning
Authors: Mark Vero, Mislav Balunovic, Dimitar Iliev Dimitrov, Martin Vechev
ICML 2023 | Venue PDF | LLM Run Details | Input Tokens: 39,952 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,103 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate Tab Leak on four tabular datasets for both Fed SGD and Fed Avg training protocols, and show that it successfully breaks several settings previously deemed safe. |
| Researcher Affiliation | Academia | 1Department of Information Technology and Electrical Engineering, ETH Zurich, Zurich, Switzerland 2Department of Computer Science, ETH Zurich, Zurich, Switzerland. |
| Pseudocode | Yes | Algorithm 1 Tab Leak against training by Fed SGD |
| Open Source Code | Yes | Our code is available at: https://github.com/eth-sri/tableak. |
| Open Datasets | Yes | All experiments were carried out on four popular mixed-type tabular binary classification datasets, the Adult census dataset (Dua & Graff, 2017), the German Credit dataset (Dua & Graff, 2017), the Lawschool Admission dataset (Wightman, 2017), and the Health Heritage dataset from Kaggle (2012). |
| Dataset Splits | No | The paper discusses training models and observing their performance on a 'secluded test set' and mentions a 'separate validation set' in a general discussion on preventing overfitting, but it does not specify explicit training/validation/test splits (e.g., percentages or counts) for its own experimental setup to reproduce the data partitioning. |
| Hardware Specification | Yes | We ran each of our experiments on single cores of Intel(R) Xeon(R) CPU E5-2690 v4 @ 2.60GHz. |
| Software Dependencies | No | The paper mentions using the 'Adam optimizer' but does not provide specific version numbers for any software or libraries used in the experiments (e.g., 'PyTorch 1.9'). |
| Experiment Setup | Yes | For all attacks, we use the Adam optimizer (Kingma & Ba, 2015) with learning rate 0.06 for 1 500 iterations and without a learning rate schedule to perform the optimization in Alg. 1. |