Privacy-Enhanced Zero-Order Federated Learning Using Multi-Key Homomorphic Encryption Over Wireless Channels
Researchers propose a new protocol that combines multi-key homomorphic encryption (xMK-CKKS) with federated learning over wireless channels, enabling secure aggregation without requiring channel estimation. The method assigns each device its own encryption key, providing stronger security against compromised clients compared to existing single-key approaches. This advancement is significant for privacy-preserving machine learning in distributed systems where wireless communication and data security are critical concerns.
The paper introduces a four-phase protocol that aggregates encrypted data from multiple federated learning participants over a shared wireless channel without needing channel estimation or pre-equalization. By leveraging multi-key homomorphic encryption, the approach assigns each device an individual secret key, preventing honest-but-curious clients from recovering other participants' local updates—a vulnerability in existing single-key schemes. The protocol works by retransmitting partial public keys and ciphertexts through the same channel, allowing dominant encryption terms to cancel algebraically during decryption. When integrated with zero-order federated learning on slowly varying line-of-sight dominant channels, each device transmits only a single encrypted scalar per round, making communication and encryption overhead independent of model dimension. Theoretical analysis shows the protocol maintains standard convergence rates of O(1/√K) up to a negligible noise floor, with validation on MNIST datasets.
What's missing
The study's limitations include: validation only on MNIST (a relatively simple benchmark); assumption of slowly varying LoS-dominant channels, which may not reflect all real-world wireless environments; and no comparison with computational overhead or latency against existing HE-based federated learning methods. The paper does not discuss scalability to large numbers of devices or performance on more complex datasets and models.
What different sources said
- arXiv cs.LGCenter
Privacy-Enhanced Zero-Order Federated Learning via xMK-CKKS over Wireless Channels
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.