GradCloak: Gradient Obfuscation for Privacy-Preserving Distributed Learning as a Service
- 16 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (2) , 1277-1290
Abstract
Gradient leakage attacks pose a significant privacy threat in distributed learning-as-a-service APIs. Existing literature on gradient leakage defense relies on gradient perturbation for preventing privacy leakage. However, determining where and how much to perturb the gradient offers different capabilities for preventing gradient leakage. This paper presents GradCloak, a principled approach to guiding gradient perturbation with theoretical robustness bounds in federated learning as a service, aiming to find the minimum required noise for simultaneously achieving privacy protection, competitive accuracy, and preventing gradient leakage attacks. The paper is organized into three major components. First, we formulate the gradient leakage threats and their adverse effect. We categorize the attack into two broad types: leakage during local training and leakage before global aggregation. Second, we investigate different gradient perturbation approaches. We analyze and compare these gradient perturbation methods, which are performed at the federated server, with those performed at the participating client(s). Third, we introduce three robustness properties of robust perturbation against gradient leakage threats, formulated by the anonymization bound for training data robustness, the perturbation bound for gradient robustness, and the distribution robustness bound for perturbed gradients. We conduct extensive evaluations on eight benchmark datasets to demonstrate that specific settings of gradient perturbation exist that best balance privacy, accuracy, and leakage prevention. Code is available at https://github.com/git-disl/GradCloak.Keywords
Funding Information
- Fordham Faculty Research
- Fordham AI Research
- NSF CISE (2302720)
- NSF CISE (2312758)
- IBM Faculty Award
- CISCO Edge AI Program
This publication has 35 references indexed in Scilit:
- ALDP-FL for adaptive local differential privacy in federated learningScientific Reports, 2025
- Shadow defense against gradient inversion attack in federated learningMedical Image Analysis, 2025
- Blockchain-based optimized edge node selection and privacy preserved framework for federated learningCluster Computing, 2023
- When the Curious Abandon Honesty: Federated Learning Is Not Private2023
- See through Gradients: Image Batch Recovery via GradInversion2021
- Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective2021
- Federated Learning for Internet of Things: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2021
- A Framework for Evaluating Client Privacy Leakages in Federated Learning2020
- Rényi Differential Privacy2017
- Calibrating Noise to Sensitivity in Private Data Analysis2006