Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning

• URL: http://arxiv.org/abs/2609.03851v1
• Date: Thu, 03 Sep 2026 13:43:32 GMT
• Title: Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning
• Abstract summary: Federated Learning with Differential Privacy (DP) is increasingly adopted to preserve data confidentiality in distributed machine learning.<n>DP noise distorts learned representations and degrades explanation fidelity, limiting differentially private FL where trustworthy explanations are required.<n>We propose XCal-FL, a closed-loop, explainability-driven local training algorithm for image classification in cross-silo FL.
• Score: 5.014410175648809
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Federated Learning (FL) with Differential Privacy (DP) is increasingly adopted to preserve data confidentiality in distributed machine learning. However, DP noise distorts learned representations and degrades explanation fidelity, limiting differentially private FL where trustworthy explanations are required, such as assistive clinical diagnosis. Prior work adapted DP noise with static feature-importance signals, restricting explainability to post hoc analysis and precluding noise calibration to explanation quality during training. We propose XCal-FL, a closed-loop, explainability-driven local training algorithm for image classification in cross-silo FL that dynamically calibrates DP noise from three complementary signals: (1) prediction logit variations, measuring causal influence on model confidence, (2) counterfactual margins, capturing decision-boundary sensitivity, and (3) saliency concentration, quantifying spatial coherence of model attention, while enforcing formal DP guarantees via adaptive privacy accounting. Experiments on three medical imaging datasets across varying FL configurations show that XCal-FL yields more accurate and interpretable global models, improving predictive performance by over 10\% and explanation fidelity by up to 5$\times$ over static-noise FL, and outperforming state-of-the-art adaptive DP methods in fidelity. XCal-FL also achieves higher privacy-budget efficiency, turning each unit of cumulative privacy loss into larger gains in both accuracy and explanation fidelity. Our analysis further reveals that, unlike predictive performance, which scales roughly linearly with privacy loss, explanation fidelity exhibits non-linear dynamics. These findings suggest explainability is a distinct dimension of the privacy trade-off that cannot be inferred from utility alone, with implications for training and privacy-budget allocation in decision-critical applications.

Related papers

• Improving Parameter-Efficient Federated Learning with Differentially Private Refactorization [8.171217925484921]
  Federated Learning (FL) with parameter-efficient fine-tuning enables scalable model training on distributed data.<n>Low-Rank Adaptation (LoRA) often introduces errors during global aggregation and amplifies the negative effect of Differential Privacy (DP)<n>We propose FedPower, a differentially private cross-silo FL framework that reshapes server-side aggregation.
  arXiv  Detail & Related papers  (2026-05-08T20:06:09Z)
• An Adaptive Differentially Private Federated Learning Framework with Bi-level Optimization [10.218291445871435]
  Federated learning enables collaborative model training across distributed clients while preserving data privacy.<n>In practical deployments, device heterogeneity, non-independent, and identically distributed (Non-IID) data often lead to highly unstable and biased gradient updates.<n>We propose an adaptive differentially private federated learning framework that explicitly targets model efficiency under heterogeneous and privacy-constrained settings.
  arXiv  Detail & Related papers  (2026-02-06T16:27:33Z)
• Explainable Differential Privacy-Hyperdimensional Computing for Balancing Privacy and Transparency in Additive Manufacturing Monitoring [5.282482641822561]
  This study introduces the Differential Privacy-Hyperdimensional Computing (DP-HD) framework.<n>DP-HD enables precise tuning of DP noise levels, ensuring an optimal balance between privacy and performance.<n>It holds substantial promise for broader applications in privacy-sensitive domains such as healthcare, financial services, and government data management.
  arXiv  Detail & Related papers  (2024-07-09T17:42:26Z)
• Privacy-preserving Federated Primal-dual Learning for Non-convex and Non-smooth Problems with Model Sparsification [51.04894019092156]
  Federated learning (FL) has been recognized as a rapidly growing area, where the model is trained over clients under the FL orchestration (PS) In this paper, we propose a novel primal sparification algorithm for and guarantee non-smooth FL problems. Its unique insightful properties and its analyses are also presented.
  arXiv  Detail & Related papers  (2023-10-30T14:15:47Z)
• Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learning [86.08285033925597]
  This paper presents a new DP perturbation mechanism with a time-varying noise amplitude to protect the privacy of federated learning. We derive an online refinement of the series to prevent FL from premature convergence resulting from excessive perturbation noise. The contribution of the new DP mechanism to the convergence and accuracy of privacy-preserving FL is corroborated, compared to the state-of-the-art Gaussian noise mechanism with a persistent noise amplitude.
  arXiv  Detail & Related papers  (2023-03-07T22:52:40Z)
• Balancing Privacy Protection and Interpretability in Federated Learning [8.759803233734624]
  Federated learning (FL) aims to collaboratively train the global model in a distributed manner by sharing the model parameters from local clients to a central server. Recent studies have illustrated that FL still suffers from information leakage as adversaries try to recover the training data by analyzing shared parameters from local clients. We propose a simple yet effective adaptive differential privacy (ADP) mechanism that selectively adds noisy perturbations to the gradients of client models in FL.
  arXiv  Detail & Related papers  (2023-02-16T02:58:22Z)
• Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations [57.20885629270732]
  We consider privacy aspects of wireless federated learning with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. Traditional perturbation-based methods provide privacy protection while sacrificing the training accuracy. In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server.
  arXiv  Detail & Related papers  (2022-10-05T13:13:35Z)
• 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)
• On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times [51.61278695776151]
  Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively. Recent studies have pointed out that the naive FL is susceptible to gradient leakage attacks. Differential Privacy (DP) emerges as a promising countermeasure to defend against gradient leakage attacks.
  arXiv  Detail & Related papers  (2021-01-11T19:43:12Z)
• RDP-GAN: A R\'enyi-Differential Privacy based Generative Adversarial Network [75.81653258081435]
  Generative adversarial network (GAN) has attracted increasing attention recently owing to its impressive ability to generate realistic samples with high privacy protection. However, when GANs are applied on sensitive or private training examples, such as medical or financial records, it is still probable to divulge individuals' sensitive and private information. We propose a R'enyi-differentially private-GAN (RDP-GAN), which achieves differential privacy (DP) in a GAN by carefully adding random noises on the value of the loss function during training.
  arXiv  Detail & Related papers  (2020-07-04T09:51:02Z)
• 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.