Approximating Two-Layer ReLU Networks for Hidden State Analysis in Differential Privacy

• URL: http://arxiv.org/abs/2407.04884v2
• Date: Fri, 11 Oct 2024 11:26:44 GMT
• Title: Approximating Two-Layer ReLU Networks for Hidden State Analysis in Differential Privacy
• Authors: Antti Koskela,
• Abstract summary: We show that it is possible to privately train convex problems with privacy-utility trade-offs comparable to those of one hidden-layer ReLU networks trained with DP-SGD. Our experiments on benchmark classification tasks show that NoisyCGD can achieve privacy-utility trade-offs comparable to DP-SGD applied to one-hidden-layer ReLU networks.
• Score: 3.8254443661593633
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The hidden state threat model of differential privacy (DP) assumes that the adversary has access only to the final trained machine learning (ML) model, without seeing intermediate states during training. Current privacy analyses under this model, however, are limited to convex optimization problems, reducing their applicability to multi-layer neural networks, which are essential in modern deep learning applications. Additionally, the most successful applications of the hidden state privacy analyses in classification tasks have been for logistic regression models. We demonstrate that it is possible to privately train convex problems with privacy-utility trade-offs comparable to those of one hidden-layer ReLU networks trained with DP stochastic gradient descent (DP-SGD). We achieve this through a stochastic approximation of a dual formulation of the ReLU minimization problem which results in a strongly convex problem. This enables the use of existing hidden state privacy analyses, providing accurate privacy bounds also for the noisy cyclic mini-batch gradient descent (NoisyCGD) method with fixed disjoint mini-batches. Our experiments on benchmark classification tasks show that NoisyCGD can achieve privacy-utility trade-offs comparable to DP-SGD applied to one-hidden-layer ReLU networks. Additionally, we provide theoretical utility bounds that highlight the speed-ups gained through the convex approximation.

Related papers

• Sparsity-Preserving Differentially Private Training of Large Embedding Models [67.29926605156788]
  DP-SGD is a training algorithm that combines differential privacy with gradient descent. Applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. We present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models.
  arXiv  Detail & Related papers  (2023-11-14T17:59:51Z)
• Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks [72.51255282371805]
  We prove a privacy bound for the KL divergence between model distributions on worst-case neighboring datasets. We find that this KL privacy bound is largely determined by the expected squared gradient norm relative to model parameters during training.
  arXiv  Detail & Related papers  (2023-10-31T16:13:22Z)
• DP-SGD with weight clipping [1.0878040851638]
  We present a novel approach that mitigates the bias arising from traditional gradient clipping. By leveraging a public upper bound of the Lipschitz value of the current model and its current location within the search domain, we can achieve refined noise level adjustments.
  arXiv  Detail & Related papers  (2023-10-27T09:17:15Z)
• Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses [4.68299658663016]
  The Noisy-SGD algorithm is widely used for privately training machine learning models. Recent findings have shown that if the internal state remains hidden, then the privacy loss might remain bounded. We address this problem for DP-SGD, a popular variant of Noisy-SGD that incorporates gradient clipping to limit the impact of individual samples on the training process.
  arXiv  Detail & Related papers  (2023-05-17T02:25:56Z)
• FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations [53.268801169075836]
  We propose FedLAP-DP, a novel privacy-preserving approach for federated learning. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes. Our approach presents a faster convergence speed compared to typical gradient-sharing methods.
  arXiv  Detail & Related papers  (2023-02-02T12:56:46Z)
• A Differentially Private Framework for Deep Learning with Convexified Loss Functions [4.059849656394191]
  Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and output perturbation. We propose a novel output perturbation framework by injecting DP noise into a randomly sampled neuron.
  arXiv  Detail & Related papers  (2022-04-03T11:10:05Z)
• Differentially Private Learning Needs Hidden State (Or Much Faster Convergence) [9.429448411561541]
  We show that differentially private learning, with a tight bound, needs hidden state privacy analysis or a fast convergence. Our converging privacy analysis, thus, shows that differentially private learning, with a tight bound, needs hidden state privacy analysis or a fast convergence.
  arXiv  Detail & Related papers  (2022-03-10T13:31:08Z)
• DP-UTIL: Comprehensive Utility Analysis of Differential Privacy in Machine Learning [3.822543555265593]
  Differential Privacy (DP) has emerged as a rigorous formalism to reason about privacy leakage. In machine learning (ML), DP has been employed to limit/disclosure of training examples. For deep neural networks, gradient perturbation results in lowest privacy leakage.
  arXiv  Detail & Related papers  (2021-12-24T08:40:28Z)
• Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence [73.14373832423156]
  We propose DP-Sinkhorn, a novel optimal transport-based generative method for learning data distributions from private data with differential privacy. Unlike existing approaches for training differentially private generative models, we do not rely on adversarial objectives.
  arXiv  Detail & Related papers  (2021-11-01T18:10:21Z)
• Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning [74.73901662374921]
  A differentially private model degrades the utility drastically when the model comprises a large number of trainable parameters. We propose an algorithm emphGradient Embedding Perturbation (GEP) towards training differentially private deep models with decent accuracy.
  arXiv  Detail & Related papers  (2021-02-25T04:29:58Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.