Research
Tight Auditing of Differential Privacy in MST and AIM
arXiv:2604.18352v1 Announce Type: cross Abstract: State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarant
arXiv:2604.18352v1 Announce Type: cross Abstract: State-of-the-art Differentially Private (DP) synthetic data generators such as MST and AIM are widely used, yet tightly auditing their privacy guarantees remains challenging. We introduce a Gaussian Differential Privacy (GDP)-based auditing framework that measures privacy via the full false-positive/false-negative tradeoff. Applied to MST and AIM under worst-case settings, our method provides the first tight audits in the strong-privacy regime. For (epsilon,elta)=(1,10^{-2}), we obtain mu_{emp}approx0.43 vs. implied mu=0.45, showing a small theory-practice gap. Our code is publicly available: https://github.com/sassoftware/dpmm.
Related
- Refined Differentially Private Linear Regression via Extension of a Free Lunch Result
- DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
- Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
- Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks
Source: arXiv cs.LG | 2026-04-21