A Sharp Transition in Data Reconstruction under Differential Privacy
cs.LG, cs.AI, stat.ML
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Protection Against Reconstruction and Its Applications in Private Federated Learning
- High-Dimensional Private Linear Regression with Optimal Rates
- Unlocking High-Accuracy Differentially Private Image Classification through Scale
- Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy
- Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms
- Reconstructing Training Data From Real World Models Trained with Transfer Learning
- Defending against Reconstruction Attacks with R'enyi Differential Privacy
- A Unified Framework for Adversary-Aware Differential Privacy Bounds
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks