English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The federated learning (FL) technique was developed to mitigate data privacyissues in the traditional machine learning paradigm. While FL ensures that auser's data always remain with the user, the gradients are shared with thecentralized server to build the global model. This results in privacy leakage,where the server can infer private information from the shared gradients. Tomitigate this flaw, the next-generation FL architectures proposed encryptionand anonymization techniques to protect the model updates from the server.However, this approach creates other challenges, such as malicious userssharing false gradients. Since the gradients are encrypted, the server isunable to identify rogue users. To mitigate both attacks, this paper proposes anovel FL algorithm based on a fully homomorphic encryption (FHE) scheme. Wedevelop a distributed multi-key additive homomorphic encryption scheme thatsupports model aggregation in FL. We also develop a novel aggregation schemewithin the encrypted domain, utilizing users' non-poisoning rates, toeffectively address data poisoning attacks while ensuring privacy is preservedby the proposed encryption scheme. Rigorous security, privacy, convergence, andexperimental analyses have been provided to show that FheFL is novel, secure,and private, and achieves comparable accuracy at reasonable computational cost.

FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users