Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
March 29, 2026Artificial Intelligence ReviewOpen Access

Privacy-preserving in foundation models: a systematic review of techniques, threats, and trade-offs

View Full Paper
Ask AI
Bookmark
Share

Authors

AEAbdallah M. ElSheikhJRJ. RokneRAR. Alhajj

Discussion

Loading...

Member takes

Overview

This systematic review analyzes privacy-preserving techniques in foundation models, suggesting improvements for ethical AI design.

Key Points

  • The review aims to identify and evaluate privacy-preserving techniques and threats in foundation models.
  • Conducted a systematic literature review of 295 peer-reviewed studies.
  • Analyzed privacy-preserving techniques across the foundation model lifecycle.
  • Evaluated privacy threats and challenges related to foundation models.
  • Investigated privacy-utility trade-offs in existing literature.
  • Identified various privacy-preserving techniques and their applications in foundation models.
  • Highlighted common privacy threats and their prevalence.
  • Discussed challenges in implementing effective privacy measures.
  • Provided a taxonomy for understanding privacy-preserving techniques and threats.

Cite This Study

ElSheikh et al. (2026) studied this question.

synapsesocial.com/papers/69c8c28cde0f0f753b39cf12https://doi.org/10.1007/s10462-026-11535-4
View Full Paper
Ask AI
Bookmark
Share