New Federated Learning Framework Combines Differential Privacy and Secure Aggregation for Enhanced Data Protection
Researchers have proposed DDP-SA, a federated learning framework that combines local differential privacy with additive secret sharing to protect user data during distributed model training. The system uses a two-stage mechanism where clients add calibrated noise to their data before splitting it across multiple servers, ensuring no single server can reconstruct individual contributions. The approach aims to close a gap between existing privacy methods by offering stronger end-to-end guarantees without prohibitive computational costs.
DDP-SA is a privacy-preserving federated learning framework submitted for review at IEEE Transactions on Dependable and Secure Computing, developed to address limitations in current approaches that rely on either differential privacy or secure multi-party computation alone. In the first stage, participating clients perturb their local model gradients using calibrated Laplace noise, a form of local differential privacy. In the second stage, these noisy gradients are decomposed into additive secret shares distributed across multiple intermediate servers, so that no single server or intercepted communication channel can reveal any individual client's data. The central parameter server only ever reconstructs the aggregated noisy gradient, never any client-specific update. Experiments reported by the authors indicate that DDP-SA achieves higher model accuracy than standalone local differential privacy while providing stronger privacy guarantees than MPC-only methods, and the framework scales linearly with the number of participants.
What's missing
The paper is a preprint under review and has not yet been peer-reviewed or published. Key open questions include: how DDP-SA performs under realistic adversarial threat models with colluding servers, how the accuracy-privacy tradeoff behaves across different datasets and tasks beyond those tested, and whether the linear scalability claim holds under heterogeneous or unreliable network conditions typical of real-world federated deployments. The specific datasets and baselines used in experiments are not described in the abstract.
What different sources said
- arXiv cs.LGCenter
FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projection
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.