Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGD
cs.LG, cs.CR
Submitted: 2026-10-07
Updated: 2026-10-07
Code: https://github.com/bilgehanertan/closed-form-noise-calibration
Terminology
Sources
- Deep Learning with Gaussian Differential Privacy
- Privacy Amplification for BandMF via $b$-Min-Sep Subsampling
- Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
- Gaussian Differential Privacy
- Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
- Tighter Privacy Analysis for Truncated Poisson Sampling
- Harnessing large-language models to generate private synthetic text
- Shuffle Gaussian Mechanism for Differential Privacy
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms
- Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
- Trade-off Functions for DP-SGD with Subsampling based on Random Allocation: Tight Upper and Lower Bounds
- Rethinking the Security of DP-SGD: A Corrected Analysis of Differentially Private Machine Learning
- Opacus: User-Friendly Differential Privacy Library in PyTorch
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