Jul 2026· 2026 3rd World Conference on Computer and Information Security (WCCIS)· pp. 186-189· 0 citations· 12 references
Abstract
Federated learning (FL) is a machine learning technique where multiple clients with local data collaborate in training a machine learning model. However, this centralization of sensitive model updates incurs security and privacy issues. A malicious aggregator can launch inference attacks to violate the privacy of clients' private data from local models and explore sensitive knowledge from global model. Trusted Execution Environment (TEE) based schemes offer secure enclaves to protect models privacy during the aggregation procedure. However, TEE technologies incur new functional and security assumptions, where a single vulnerability could undermine the trusted system. Cryptographic schemes such as homomorphic encryption (HE), differential privacy (DP) and secret sharing (SS) cannot achieve the simultaneous requirements of efficiency, accuracy and privacy currently. In this paper, we present DoshFL that avoids expensive cryptographic operations and enables tunable trade-off between privacy and efficiency in federated learning for model asset protection.
The research findings suggest that improved federated learning can achieve an optimal predictive performance, privacy protection, and secure collaborative learning, which makes it a viable method for next-generation distributed AI systems.
Sheetal Bawane, Leeladhar Chourasiya, S. Jain et al.· International journal of com...· 0 citations
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
This paper proposes a comprehensive framework for privacy-preserving feature engineering (PPFE) within federated learning analytics and explores techniques such as homomorphic encryption, differential privacy, and secure multi-party computation to enable robust, privacy-safe feature selection, transformation, and extraction across clients.
Yuki Nakamura, Olivia Martin· International Journal of Dat...· 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
Training machine learning models across many institutions without moving raw data is attractive in theory, but the standard Federated Learning setup hands enormous power to one central aggregation server that participants must trust blindly. what happens when that trust assumption is violated and build a system, that does not require it. couples a four-layer distributed architecture with three stacked privacy mechanisms Local Differential Privacy to bound what any single gradient reveals, Secure Multi-Party Computation via the SecAgg protocol so the aggregation server never sees individual updates, and Tendermint-BFT blockchain consensus to create a tamper-evident audit log that no single party controls. Our main technical contribution is a formal proof that the combination of LDP and SecAgg satisfies end-to-end $(\varepsilon, \delta)$-differential privacy, including the SecAgg masking step cannot degrade the DP guarantee already earned by LDP noise injection. On CIFAR-10 with a ResNet-18 under three Dirichlet non-IID splits tested on real cluster hardware, reached 78.3% accuracy at $\varepsilon=0.83$ against six baselines including FedProx and SCAFFOLD-two standard non-IID benchmarks that prior blockchain FL work has consistently omitted.
Raman Dubey, A. Jain, Richa Sharma· International Conference on...· 0 citations
Decentralized Federated Learning (DFL) enables collaborative artificial intelligence model training without centralizing sensitive data, making it suitable for privacy-critical and distributed intelligent systems such as healthcare, Industrial IoT, and smart digital infrastructure. Despite its advantages, DFL remains vulnerable to privacy leakage through shared model updates and to model poisoning and backdoor attacks that compromise system reliability, robustness, and trustworthiness. Existing defense mechanisms primarily address either privacy preservation or poisoning robustness independently and often exhibit limited effectiveness under adaptive or high-ratio adversarial settings. This work proposes a trustworthy and privacy-preserving decentralized federated learning framework that jointly addresses these challenges through two integrated components: (i) a hybrid privacy mechanism based on public dataset pretraining followed by differentially private fine-tuning, and (ii) a multi-layer model defense architecture designed to mitigate poisoning and backdoor attacks across decentralized peer-to-peer environments. The framework integrates local data sanitization, peer-side model verification, robust trimmed-mean aggregation, and runtime inference protection to provide defense-in-depth across both training-time and inference-time attack surfaces. An adversary model and operational assumptions are formally defined, and the framework is evaluated under strong adversarial conditions, including a 20% poisoning ratio. Experimental results demonstrate consistent robustness improvements over a vanilla DFL baseline. While the baseline model achieves a clean accuracy of 83.10%, the proposed framework improves clean performance to 86.12%. Under adversarial conditions, accuracy improves from 37.71% to 53.88% for Fast Gradient Sign Method (FGSM) attacks, from 21.75% to 46.40% for Projected Gradient Descent (PGD) attacks, and from 40.62% to 67.35% for Carlini–Wagner (CW) attacks. For backdoor-based poisoning attacks such as BadNets and Blended attacks, the defense pipeline restores model accuracy to above 86% while maintaining stable benign performance. 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
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
