Private and Stable Test-Time Adaptation with Differential Privacy

• URL: http://arxiv.org/abs/2606.01908v1
• Date: Mon, 01 Jun 2026 08:45:59 GMT
• Title: Private and Stable Test-Time Adaptation with Differential Privacy
• Abstract summary: Test-time adaptation (TTA) can reduce error on new and different data by updating the model on these inputs during inference.<n>These updates raise the issue of privacy w.r.t. the testing data, because the model parameters now depend on all past inputs.<n>To control this privacy risk, we cast multiple popular TTA methods into differential privacy forms.<n>On ImageNet-C, our DP-TTA methods provide adequate privacy at small cost to accuracy, and in the low-privacy regime the clipping mechanism of DP can even improve the accuracy and stability of adaptation.
• Score: 6.479634870242713
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time adaptation (TTA) can reduce error on new and different data by updating the model on these inputs during inference. However, these updates raise the issue of privacy w.r.t. the testing data, because the model parameters now depend on all past inputs. To control this privacy risk, we cast multiple popular TTA methods (Tent, EATA, SAR, DeYO, and COME) into differential privacy (DP) forms that apply per-sample gradient clipping and Gaussian noise for all updates. On ImageNet-C, our DP-TTA methods provide adequate privacy at small cost to accuracy, and in the low-privacy regime the clipping mechanism of DP can even improve the accuracy and stability of adaptation in the continual setting. These improvements to privacy and accuracy come at only modest computational overhead. These first results on private TTA raise awareness of the issue, inform the development of more private test-time updates, and identify per-sample clipping as an effective technique for improving the accuracy and stability of adaptation.

Related papers

• Meta-Learning and Targeted Differential Privacy to Improve the Accuracy-Privacy Trade-off in Recommendations [8.550044487436132]
  Balancing differential privacy with recommendation accuracy is a key challenge in privacy-preserving recommender systems.<n>We address this trade-off at both the data and model levels.<n>We use meta-learning to improve robustness to remaining DP-noise.
  arXiv  Detail & Related papers  (2026-04-29T08:00:20Z)
• Evaluation of Differential Privacy Mechanisms on Federated Learning [0.0]
  Federated learning is distributed across several clients without disclosing raw data.<n> Differential Privacy (DP) is a technique to protect sensitive data by adding noise to model updates.<n>This work implements DP methods using Laplace and Gaussian mechanisms with an adaptive privacy budget.
  arXiv  Detail & Related papers  (2025-10-09T11:32:36Z)
• AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks [1.7265013728931]
  We propose a new differentially private SGD framework with importance-based gradient updates tailored for deep neural networks.<n>AdaDPIGU satisfies $(varepsilon, delta)$-differential privacy and retains convergence guarantees.<n>On MNIST, our method achieves a test accuracy of 99.12% under a privacy budget of $epsilon = 8$, nearly matching the non-private model.
  arXiv  Detail & Related papers  (2025-07-09T03:53:03Z)
• Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning [59.29849532966454]
  We propose PseudoProbability Unlearning (PPU), a novel method that enables models to forget data to adhere to privacy-preserving manner. Our method achieves over 20% improvements in forgetting error compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-11-04T21:27:06Z)
• Private Fine-tuning of Large Language Models with Zeroth-order Optimization [51.19403058739522]
  Differentially private gradient descent (DP-SGD) allows models to be trained in a privacy-preserving manner.<n>We introduce DP-ZO, a private fine-tuning framework for large language models by privatizing zeroth order optimization methods.
  arXiv  Detail & Related papers  (2024-01-09T03:53:59Z)
• Privacy Constrained Fairness Estimation for Decision Trees [2.9906966931843093]
  Measuring the fairness of any AI model requires the sensitive attributes of the individuals in the dataset. We propose a novel method, dubbed Privacy-Aware Fairness Estimation of Rules (PAFER) We show that using the Laplacian mechanism, the method is able to estimate SP with low error while guaranteeing the privacy of the individuals in the dataset with high certainty.
  arXiv  Detail & Related papers  (2023-12-13T14:54:48Z)
• DP-SGD-Global-Adapt-V2-S: Triad Improvements of Privacy, Accuracy and Fairness via Step Decay Noise Multiplier and Step Decay Upper Clipping Threshold [1.8741812670237725]
  DPSGD's per-sample gradient clipping and uniform noise addition during training can significantly degrade model utility and fairness.<n>We develop the DP-SGD-Global-Adapt-V2-S, which has a step-decay noise multiplier and an upper clipping threshold that is also decayed step-wise.<n>It improves accuracy by 0.9795%, 0.6786%, and 4.0130% in MNIST, CIFAR10, and CIFAR100, respectively.
  arXiv  Detail & Related papers  (2023-12-05T00:09:57Z)
• A Randomized Approach for Tight Privacy Accounting [63.67296945525791]
  We propose a new differential privacy paradigm called estimate-verify-release (EVR) EVR paradigm first estimates the privacy parameter of a mechanism, then verifies whether it meets this guarantee, and finally releases the query output. Our empirical evaluation shows the newly proposed EVR paradigm improves the utility-privacy tradeoff for privacy-preserving machine learning.
  arXiv  Detail & Related papers  (2023-04-17T00:38:01Z)
• TAN Without a Burn: Scaling Laws of DP-SGD [70.7364032297978]
  Differentially Private methods for training Deep Neural Networks (DNNs) have progressed recently. We decouple privacy analysis and experimental behavior of noisy training to explore the trade-off with minimal computational requirements. We apply the proposed method on CIFAR-10 and ImageNet and, in particular, strongly improve the state-of-the-art on ImageNet with a +9 points gain in top-1 accuracy.
  arXiv  Detail & Related papers  (2022-10-07T08:44:35Z)
• Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent [69.14164921515949]
  We characterize privacy guarantees for individual examples when releasing models trained by DP-SGD. We find that most examples enjoy stronger privacy guarantees than the worst-case bound. This implies groups that are underserved in terms of model utility simultaneously experience weaker privacy guarantees.
  arXiv  Detail & Related papers  (2022-06-06T13:49:37Z)
• Dynamic Differential-Privacy Preserving SGD [19.273542515320372]
  Differentially-Private Gradient Descent (DP-SGD) prevents training-data privacy breaches by adding noise to the clipped gradient during SGD training. The same clipping operation and additive noise across training steps results in unstable updates and even a ramp-up period. We propose the dynamic DP-SGD, which has a lower privacy cost than the DP-SGD during updates until they achieve the same target privacy budget.
  arXiv  Detail & Related papers  (2021-10-30T04:45:11Z)
• 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)
• Privacy Preserving Recalibration under Domain Shift [119.21243107946555]
  We introduce a framework that abstracts out the properties of recalibration problems under differential privacy constraints. We also design a novel recalibration algorithm, accuracy temperature scaling, that outperforms prior work on private datasets.
  arXiv  Detail & Related papers  (2020-08-21T18:43:37Z)
• 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.