Practical Differentially Private and Byzantine-resilient Federated Learning

Published version (SIGMOD 2023): https://dl.acm.org/doi/10.1145/3589264. Full version paper (including appendix) can be found at https://arxiv.org/abs/2304.09762

To reproduce

Install all packages as specified in requirements.txt.

Install packages as described in "requirements.txt"

Open "\datasets\dataset_setup.py", edit function "get_dataset_data_path" to return the path you specified to store the dataset source file.

Check the setups in script *.sh, then run it in a terminal.

Reference

@article{DBLP:journals/pacmmod/Xiang0L023,
  author       = {Zihang Xiang and
                  Tianhao Wang and
                  Wanyu Lin and
                  Di Wang},
  title        = {Practical Differentially Private and Byzantine-resilient Federated
                  Learning},
  journal      = {Proc. {ACM} Manag. Data},
  volume       = {1},
  number       = {2},
  pages        = {119:1--119:26},
  year         = {2023},
  url          = {https://doi.org/10.1145/3589264},
  doi          = {10.1145/3589264},
  timestamp    = {Fri, 07 Jul 2023 23:32:32 +0200},
  biburl       = {https://dblp.org/rec/journals/pacmmod/Xiang0L023.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}