Privacy-Preserving and Verifiable Approximate Distributed Coded Computing
2026-07-02 • Machine Learning
Machine LearningCryptography and Security
AI summaryⓘ
The authors propose a new system that helps multiple computers learn together without sharing their raw data, while also protecting against spying and cheating. Their approach works for different types of distributed learning, like federated learning and decentralized learning, by combining special privacy techniques with ways to catch and reduce bad behavior. They tested their system against common attacks and showed it can keep data safer and handle malicious actions better than previous methods. This means their method could be useful for securely training models across many devices.
distributed machine learningfederated learningdecentralized learningprivacy preservationadversary resistancerobust aggregationcoded computingprivacy attacksgroup testingmodel training
Authors
Xavier Martínez-Luaña, Alba Gude-Santos, Manuel Fernández-Veiga, Rebeca P. Díaz-Redondo
Abstract
Distributed machine learning enables collaborative model training without centralizing data, but it also exposes learning processes to privacy leakage and malicious manipulation. Existing defenses typically address these threats in isolation and are often tailored to specific learning paradigms or model architectures, limiting their applicability in realistic deployments. In particular, federated learning and decentralized learning exhibit distinct adversarial surfaces that are rarely addressed within a unified framework. In this paper, we present a model-agnostic framework for adversary-resistant distributed learning that jointly addresses privacy preservation and malicious behavior across both federated and decentralized settings. Our approach combines paradigm-specific defense mechanisms with GPBACC, a privacy-enhancing coded computing technique applicable to arbitrary machine learning models. For federated learning, we integrate robust aggregation strategies to mitigate the impact of malicious participants, while for decentralized learning we employ approximate decode-and-compare and group testing techniques to enable lightweight verification and adversary isolation without relying on a trusted aggregator. Crucially, we evaluate the proposed framework through an explicit, attack-driven analysis. We implement representative privacy attacks and malicious behaviors, and empirically demonstrate that the combination of GPBACC with robust aggregation and verification mechanisms significantly reduces privacy leakage and improves resilience against active adversaries. These results suggest that privacy-enhancing coded computing, when combined with appropriate adversary-resistance strategies, provides a practical and deployable foundation for secure distributed machine learning.