FISGuard: Defending Against Membership Inference via Fixed Input Subspaces

Abstract

As large language models are increasingly adopted in federated learning, protecting user privacy while performing parameter-efficient fine-tuning on distributed private data has become an important challenge. Although clients only share gradients instead of directly uploading raw data, the shared gradients may still leak membership information about training samples. ProjRes (S&P, 2026) further increases this risk: with less information and without accessing model outputs, an attacker can effect

Categories

Framework mappings

Suggested from the entry's categories.

@misc{jiang2026fisguard,
  title = {{FISGuard: Defending Against Membership Inference via Fixed Input Subspaces}},
  author = {Hao-Cheng Jiang and Hua Shen},
  year = {2026},
  month = aug,
  eprint = {2608.27836},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/ddc1bf96c1d3e2b92361ca225366c16b962434b3}
}