# TIGER Recovers Training Inputs From Federated Learning Gradients

A new attack reconstructs private inputs by optimizing distances in embedding subspaces, sharpening doubts about gradient sharing.

- Published: 2026-06-18T10:48:01.079Z
- Canonical: https://polylog.news/ai/2026-06-18/tiger-recovers-training-inputs-from-federated-learning-gradi
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CR](https://arxiv.org/abs/2606.18312)

A paper posted to arXiv presents TIGER, a gradient inversion attack that reconstructs private inputs from the gradient updates clients send in federated learning. The method works by inverting transformer gradients through optimization over…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-06-18/tiger-recovers-training-inputs-from-federated-learning-gradi (subscription information: https://polylog.news/pricing).