
This repository contains the source codes for USENIX Security'25 submission "SoK: On Gradient Leakage in Federated Learning" In the Zenodo repository, we provide the requirements for set up the environment in "requirements.txt". Considering that all the datasets for our experiments are public available, we provide the related URLs for downloading them in "README.md". The scripts and source codes are organized by section and chapter for clarity, relevant files are provided in "Section4.zip", "Section5.zip" and "Section6.zip". Besides, the codes for experiments in the appendix are also included in the files.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
