Unlocking High-Accuracy Differentially Private Image Classification through Scale
arXiv:2204.13650
Abstract
Differential Privacy (DP) provides a formal privacy guarantee preventing adversaries with access to a machine learning model from extracting information about individual training points. Differentially Private Stochastic Gradient Descent (DP-SGD), the most popular DP training method for deep learning, realizes this protection by injecting noise during training. However previous works have found that DP-SGD often leads to a significant degradation in performance on standard image classification benchmarks. Furthermore, some authors have postulated that DP-SGD inherently performs poorly on large models, since the norm of the noise required to preserve privacy is proportional to the model dimension. In contrast, we demonstrate that DP-SGD on over-parameterized models can perform significantly better than previously thought. Combining careful hyper-parameter tuning with simple techniques to ensure signal propagation and improve the convergence rate, we obtain a new SOTA without extra data on CIFAR-10 of 81.4% under (8, 10^{-5})-DP using a 40-layer Wide-ResNet, improving over the previous SOTA of 71.7%. When fine-tuning a pre-trained NFNet-F3, we achieve a remarkable 83.8% top-1 accuracy on ImageNet under (0.5, 8*10^{-7})-DP. Additionally, we also achieve 86.7% top-1 accuracy under (8, 8 \cdot 10^{-7})-DP, which is just 4.3% below the current non-private SOTA for this task. We believe our results are a significant step towards closing the accuracy gap between private and non-private image classification.
Cited by in corpus (6)
- How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
- The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
- DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
- LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation
- LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
- Privacy-Aware Document Visual Question Answering