The experiment showed that Autoencoder Based Federated Learning was a scalable, secure, and privacy-efficient solution to applications tailored for healthcare, finance, and other sensitive data environments.
Abstract
Today's digital age has made privacy and data protection a major concern-generally, with the kind of technologies that are turning things around and bringing everything to the cloud. FL will most likely provide a solution to the distance and make things clear in collaboration without exposing raw information from a consortium to boost its privacy. However, existing FL solutions include such challenges as increased overhead communication, risk in leaking data, and even the inefficiency of secure aggregation.To mitigate these constraints, this research proposes the Autoencoder-Based Federated Learning framework by integrating prevailing techniques such as differential privacy and homomorphic encryption that safeguard both the security and efficiency of the model. This method does not only steal model ideas for autoencoders to compress before sciences transmission but hugely reduces the transmission bandwidth and possibly minimizes gradient leakage. However, adaptive normalization is used to handle institutional heterogeneity to maintain better performance for the model. Conclusion of experimentation indicated that this framework could significantly reduce communication overhead while retaining high federated learning accuracy and even better security. Further, the trust-based client evaluation mechanism is presented to detect malicious behavior and improve reliability regarding federated aggregation. The experiment showed that Autoencoder Based Federated Learning was a scalable, secure, and privacy-efficient solution to applications tailored for healthcare, finance, and other sensitive data environments.
An in-depth analysis of federated learning methods and paying special attention to the issue of privacy is provided, which examines new developments, concerns and tradeoffs connected with privacy, effectiveness of communication, model noise, and scalability of systems.
Aarav Mehta· International Journal of App...· 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 establish efficient and secure FL system as well as maintaining competitive performance, we introduce a DP-enabled cascaded filter with novel model-aggregation mechanism. Taking the model parameters of one client for example, dimensions with large absolute values and significant variations are selected by the cascaded filter and regarded as important dimensions. After that, random noise are added to these important dimensions for data security. Finally, the model parameters will be sent to the central server for aggregation. Unlike traditional DP-based approaches, our method considers each dimension’s informational importance, i.e., both absolute value and its variation. We theoretically prove the convergence of our method and verify the effectiveness on different scenarios including four datasets. The experimental results suggest that our method outperforms the other ones from literature under both IID and non-IID conditions while achieving high level of efficiency and privacy protection performance.
Zhiqiang Chen, Yuchen Jiang, Ray Y. Zhong et al.· IEEE Transactions on Informa...· 0 citations
A federated deep learning framework that systematically integrates adaptive privacy noise mechanisms and trust-weighted aggregation within a distributed architecture that ensures the protection of sensitive data during collaborative analysis through precise differential privacy control and advanced neural network models is presented.
A novel framework for integrating privacy-preserving ML techniques within Sovereign Cloud infrastructures is presented, combining cutting-edge cryptographic approaches with the data sovereignty features of Sovereign Clouds, ensuring data privacy, legal compliance, and efficient machine learning at scale.
Ahmed Hassan· International Journal of Dat...· 0 citations
Federated learning has become a major approach for training artificial intelligence systems when data is distributed across institutions, devices, or users. Its central appeal is that raw data can remain local while model updates are coordinated through a shared training process. This paper argues that federated learning should be evaluated as a privacy-enhancing framework rather than as a complete privacy guarantee. It first identifies key privacy risks, including model-update leakage, gradient inversion, membership inference, and risks created by malicious participants. It then classifies protection mechanisms into architectural choices, optimization design, differential privacy, secure aggregation, and deployment constraints. The paper proposes a comparat ive framework that asks what federated learning protects, what it still exposes, and which auxiliary mechanisms are needed in different application settings. Healthcare AI and mobile keyboard prediction are used as contrasting case studies: the former is typically cross-silo and institutionally governed, while the latter is cross- device and large-scale. The analysis concludes that federated learning is most effective when combined with explicit threat models, layered privacy protections, security controls, and governance arrangements.
Federated learning is a technology that is used to protect data privacy in machine learning. Nonetheless, in federated learning, updating the global model requires the use of gradient descent algorithm, which involves multiple rounds of interaction between entities to complete the iterative updates, inevitably incurring massive computational and communication overhead. In 2020, Wang et al. first proposed a non-interactive federated regression scheme, which effectively improves the training efficiency of regression models while protecting the privacy of local training data. However, like most current federated regressions, it involves a third authority (TA) to generate keys for each entity, which poses a significant privacy risk and results in considerable communication overhead. From the view of security and practicality, this paper first proposes a multi-party homomorphic encryption algorithm named MPaillier. Furthermore, we have designed PNFR, a privacy-preserving federated learning scheme for regressions training built on the MPaillier algorithm. The participating entities of PNFR are the data owners and a cloud server, eliminating the need for a TA, thus enhancing the practicality and efficiency of the scheme. Experimental results demonstrate that our scheme is $\sim 10^{3}$ times faster than interactive federated regressions PrivFL and about 80% faster than non-interactive federated regressions VANE.
