Differentially private federated learning
Part of Federated and private learning
Differentially private federated learning is holding steady in AI research: 0.1% to 0.1% of new AI papers, 0.0 points. As of Oct 10, 2026.
- Change in share
- 0.0 pts
- Share, last 3 months
- 0.1%
- Papers, last 3 months
- 24
- Ready for products
- 2.4 / 5
More in Federated and private learning
Personalized federated learning0.1% → 0.1%+0.0 ptsFederated learning0.1% → 0.1%+0.0 ptsCommunication efficient federated learning0.1% → 0.1%+0.0 ptsSplit learning0.0% → 0.1%0.0 ptsSecure multiparty computation0.0% → 0.0%0.0 ptsPrivacy utility tradeoff0.0% → 0.0%0.0 ptsFederated fine tuning0.1% → 0.1%0.0 ptsHomomorphic encryption0.0% → 0.0%0.0 ptsFederated unlearning0.1% → 0.0%0.0 ptsPrivacy preserving machine learning0.1% → 0.1%0.0 pts
Differentially private federated learning: quick answers
No. Its share of new AI papers went from 0.1% to 0.1%, with 24 papers in the last 3 months.