Jul 2026· 2026 3rd World Conference on Computer and Information Security (WCCIS)· pp. 280-283· 0 citations· 8 references
Abstract
Federated learning alleviates data silos through a “data-local, model-global” paradigm, but transmitting plaintext gradients exposes clients to reconstruction attacks from malicious servers. Existing secure aggregation methods face trade-offs among privacy, accuracy, and efficiency: homomorphic encryption incurs high overhead, differential privacy sacrifices accuracy, and lightweight secret-sharing schemes often lack weighted aggregation support and suffer accuracy degradation as client numbers grow. To address these limitations, we propose SecAGG, a lossless secure weighted aggregation scheme based on additive secret sharing. SecAGG adopts a three-tier architecture consisting of client clusters, cooperative servers, and a super server. Clients split weighted model parameters into random shares and distribute them to cooperative servers, which perform encrypted partial aggregation before the super server securely reconstructs the global model. Experimental results demonstrate that SecAGG achieves strict security against up to M-1 colluding servers under the semi-honest model while preserving FedAvg-equivalent accuracy with minimal computation and communication overhead, effectively balancing privacy, accuracy, and efficiency.
To address privacy leakage in centralized aggregation, this paper proposes FedShare, a multi-server secure aggregation scheme based on additive secret sharing. It adopts a three-layer architecture (clients, ordinary aggregation servers, and a super aggregation server), where client model updates are split into secret shares and securely aggregated across servers so that no single server can access complete model parameters. To handle client data imbalance, a data-size-based weighting mechanism is applied before secret sharing to ensure consistency with FedAvg, and finite-field operations with quantization recovery are used to bound quantization errors under integer arithmetic. Experiments on MNIST and CIFAR-10 show that FedShare preserves model accuracy comparable to FedAvg while providing privacy protection, with only 7.83% and 17.21% increases in average per-round training time, demonstrating a good trade-off among privacy, utility, and efficiency.
Yuchen Jiang· 2026 3rd World Conference on...· 0 citations
Federated Learning enables data to remain on local devices, yet malicious servers can still infer sensitive user information by analyzing client-uploaded model updates, posing significant privacy leakage risks. Existing secure aggregation schemes—such as Differential Privacy, Homomorphic Encryption, and traditional Secret Sharing—struggle to achieve an ideal balance among model accuracy, computational/communication overhead, and adaptability to complex aggregation scenarios. To address this, this paper proposes a multi-server secure aggregation scheme based on additive secret sharing. The scheme introduces multiple non-colluding servers; each client splits its local model update into random secret shares and distributes them to these servers. Each server independently performs weighted aggregation, and the global model is reconstructed by a leader server. Theoretical analysis demonstrates that, owing to the linear homomorphism of additive secret sharing, the aggregation result of our scheme is mathematically equivalent to the standard FedAvg algorithm. Experimental results on the MNIST dataset show that our scheme achieves a test accuracy of 86.13% after 30 global rounds, closely matching the baseline FedAvg (86.12%), with only a 6% additional time overhead per round. Under reasonable non-collusion assumptions, the scheme achieves information-theoretic privacy protection, effectively breaking the trilemma among privacy, accuracy, and efficiency.Keywords:Federated Learning, Additive Secret Sharing,Secure Aggregation; Privacy Preservationords.
Mingyuan Li· Applied and Computational En...· 0 citations
Federated Learning (FL) enables collaborative model training while preserving privacy by keeping data local. However, the risk of sensitive data leakage through model updates necessitates the use of secure aggregation protocols. Existing server-based secure aggregation protocols typically require the server to forward sensitive data shared between users, which increases communication overhead and introduces potential security risks. In this work, we propose a novel secure aggregation protocol based on two-layer secret sharing to address these issues. By combining Shamir's Secret Sharing with 2-out-of-2 additive secret sharing using a Pseudo-Random Function (PRF), our protocol eliminates direct communication between users, thereby removing the need for the server to forward data. We further extend the protocol with Key-homomorphic PRF (KhPRF) to support high-dimensional data aggregation and apply it to FL, enabling one-shot secure aggregation with a single server and no intermediary data forwarding. To reduce user overhead, we design a new encoding method based on the Chinese Remainder Theorem for the almost KhPRF-based mask, reducing the number of KhPRF calls and mitigating the model update expansion issue after masking. Experimental results show that our scheme significantly outperforms existing methods in terms of auxiliary node overhead. For instance, when the number of users is 100, our scheme improves communication efficiency by nearly 100 times and reduces computational overhead by approximately 17\%. Moreover, user computation time can be reduced by 51\% to 75\% when the input length is $2^{18}$.
Federated Learning (FL) enables collaborative model training without centralizing client data, making it well-suited for privacy-sensitive domains. Existing approaches use techniques such as homomorphic encryption, differential privacy, and secure multi-party computation to mitigate attacks including model inversion, membership inference, and gradient leakage. However, these methods often incur high computational and memory overheads and frequently overlook confidentiality of the global model itself, which may be proprietary and sensitive. These limitations reduce the practicality of secure FL in large-scale and compliance-sensitive environments.We present NETFL, a Fully Secure and scalable FL framework that decentralizes training across client pairs using lightweight MPC, while restricting servers to secure aggregation, client pairing, and routing. NETFL eliminates server-side bottlenecks, avoids full data offloading, and preserves confidentiality of data, model parameters, and updates throughout training. Our evaluation shows that NETFL protects against unauthorized observation, reconstruction, gradient leakage, membership inference, and inversion attacks, while achieving up to 13× faster training time and 50% lower server memory usage compared to prior work.
Sahar Ghoflsaz Ghinani, Elaheh Sadredini· International Conference on...· 0 citations
Federated learning enables collaborative model training between central servers and distributed clients without collecting users' raw sensitive data, which effectively promotes the large-scale deployment of intelligent collaborative services. Considering the high sensitivity of local training data and model gradient parameters in federated learning, protecting identity privacy and interaction security has become extremely critical. Therefore, mutual identity authentication is indispensable to restrict illegal client access and prevent malicious parameter transmission and data tampering. In this paper, we propose a lightweight anonymous authentication scheme for federated learning (FedLAS), which realizes secure mutual authentication between servers and clients and establishes a shared session key for subsequent encrypted interaction. In particular, the proposed scheme eliminates the reliance on high-cost cryptographic operations such as bilinear pairing, thus minimizing computational and communication overhead. Furthermore, informal security analysis demonstrates that our FedLAS scheme can resist multiple common attacks and meet predefined security requirements. Extensive comparative experiments show that the FedLAS scheme achieves excellent performance in computational and communication cost. It is well suitable for resource-constrained federated learning scenarios.
Shu Wu, Guoqiang Meng, Linlin Lu et al.· Scientific Reports· 0 citations
It is proved that TriVer satisfies client data privacy, aggregation correctness, and aggregation-result non-forgeability in the Random Oracle Model under ECDLP hardness, HPRF pseudorandomness, and hash collision resistance, against a fully malicious server that may collude with a subset of aggregators and clients.
Guang-Ye Zhu, Liqiang Wu, Weidong Du· Journal of King Saud Univers...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
