Results show that clipping, perturbation, and the learning procedure jointly influence the observed privacy–utility behavior of centralized FL and sequential Decentralized Federated Learning.
Abstract
Centralized Federated Learning (FL) enables collaborative model training without sharing raw data. Differential privacy (DP) is widely used to protect sensitive information in FL; however, its behavior in decentralized environments remains poorly understood. This study empirically compares centralized FL and sequential Decentralized Federated Learning (DFL) under matched clipping and perturbation settings to examine model utility and privacy leakage. Both frameworks were evaluated under a common experimental setup with non-IID data, and each configuration was evaluated across five independent seeds. Utility was evaluated under matched experimental perturbation parameters, whereas formal client-level privacy accounting was applied to the perturbed round-end model releases, with each client’s complete dataset treated as the protected unit. Empirical leakage was evaluated separately using membership inference and gradient inversion attacks. Within the evaluated MNIST configuration, the results show that clipping, perturbation, and the learning procedure jointly influence the observed privacy–utility behavior. At C=1 and ϵcal=2, the mean final accuracy was 73.83% for FL and 97.74% for sequential DFL. At ϵcal=4, InvGrad reconstruction for FL produced an MSE of 0.048, PSNR of 13.71, and SSIM of 0.280, compared with 0.130, 10.10, and 0.184 for sequential DFL, respectively. Future research will investigate topology-aware privacy mechanisms and adaptive noise allocation for decentralized systems.
This thesis demonstrates that federated learning should not be considered inherently private merely because data remain decentralized, and introduces a personalized privacy-preserving federated learning framework that allows individual clients to select their preferred privacy mechanism and protection level.
The concept of Federated Learning (FL) allows training models in a decentralized way without distributing raw data but, nonetheless, the gradients are vulnerable to privacy attacks that include gradient inversion, reconstruction, and membership inference. Differential Privacy (DP) is broadly used to address these risks...
Vajjakeshavulu Anusha, Ranjeeth Kumar M· 2026 International Conferenc...· 0 citations
Federated learning (FL) enables collaborative model training across multiple clients in a privacy-preserving manner. However, the employment of homomorphic encryption algorithms might lead to high computational cost while the application of differential privacy (DP) methods would sacrifice model performance. To establi...
Zhiqiang Chen, Yuchen Jiang, Ray Y. Zhong et al.· IEEE Transactions on Informa...· 0 citations
The increasing prevalence of decentralized data has led to a growing interest in federated learning, which enables collaborative model training without clients sharing their sensitive local data. However, FL alone does not sufficiently protect sensitive training data and is generally coupled with privacy-preserving tec...
Ceren Yildirim, K. Kaya, Sinan Yıldırım et al.· 0 citations
These findings demonstrate that the proposed framework provides an effective balance between privacy preservation, adversarial robustness, and trustworthy decentralized collaborative learning for secure AI-driven systems.
Durga Sivan, Uma Maheshwari Shanmugam, Sachnev Vasily et al.· Discover Artificial Intellig...· 0 citations
RetFL is proposed, a CKKS-enabled robust aggregation framework for DFL that establishes a decentralized training workflow with VRF-based candidate selection and view change, and designs a weighted aggregation scheme that incorporates cosine similarity and a dynamic reputation mechanism to weight updates and suppress pe...
Yi-Cheng Huang, Zhou Zhou, You-Liang Tian et al.· Journal of King Saud Univers...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 9, 2026