From Pixels to Privacy-Sensitive Features: An Information-Theoretic Framework for Reconstruction Bounds
arXiv:2610.13768v1 Announce Type: new Abstract: What can an adversary recover from a model trained with DP-SGD? Its $(\varepsilon,\delta)$ guarantee does not answer this question directly. We derive a distortion bound that can be computed before training and applies even to an adversary who observe…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-12 04:00 · arXiv stat.ML
From Pixels to Privacy-Sensitive Features: An Information-Theoretic Framework for Reconstruction Bounds