Affine subspace constraints improve federated gradient inversion
The authors report better reconstruction than chosen baselines, including when batch size is moderately overestimated.
Stories per day · 30 days
6 RSS
Relatedprivacy13differential-privacy5fedavg3graph-rag3secure-aggregation3backdoor2batch-normalization2clustering2gradient-inversion2healthcare2mobilenet2post-quantum-cryptography2privacy-leakage2quantization2ssh2tls-adoption2accountability1alignment1
75 stories, newest first · one card per story
Stories tagged #federated-learning
SURA detects federated-learning backdoors with 10 clean images
It reuses one small clean proxy across repeated loss-ascent probes and restores batch-norm state only at readout.
One-shot federated clustering proposed for non-IID biomedical data
Institutions send prototypes once; a server fuses clusterlets to recover global structure while limiting computation and privacy exposure.
Zero-knowledge admission proposed for private swarm learning
Authors say the design holds 94% of clean CIFAR-100 accuracy under a gradient-scaling attack that drops FedAvg to 2.1%.
arXiv study assesses post-quantum cryptography adoption in TLS
PQC support reaches only 9.1% for HTTPS and below 1% for other protocols at server level.
arXiv proposes differentially private framework for GraphRAG
RelGuard is the first differentially private framework for GraphRAG providing formal privacy guarantees.
arXiv shows gradient inversion attacks on federated LoRA ViTs
LoRA-adapted Vision Transformers weaken gradient signals allowing private data reconstruction.
DW-FedADMM improves federated learning for Android malware detection
DW-FedADMM uses dynamic client-side weighting in federated optimization, achieving up to 97.64% accuracy on Drebin dataset with partial participation.
Federated Forensics architecture supports multi-agency learning with jurisdictional controls
New architecture blocks restricted model updates at jurisdictional borders while maintaining 93% accuracy.
arXiv proposes patient world model for health system simulation in intensive care
The model is trained on MIMIC-IV and couples time-queryable predictions to ICU calendars for simulating bed capacity and care dispatch.
arXiv proposes FedReason for LLM-based aggregation in federated learning
The LLM analyzes weights in a sandbox and submits short Python aggregation programs every ten rounds.
FedReady Uses Bounded LLM Agents for Federated Learning Formation
FedReady prepares task-specific data for federated learning with LLM agents and digest-checked contracts.
VeilFL adds two-stage accountability to anonymous federated learning
VeilFL detects duplicate submissions in PINE without persistent identifiers for normal participants using staged tracing.
Correlated quantization cuts communication in private federated RL
One-bit uploads with correlated private quantization reduce mean travel time by 14.3% while preserving privacy in vehicular networks.
AuditFL: A Contract-Backed Clearing Layer for Open Federated Learning
AuditFL adds on-chain auditability to federated learning using contract-backed tickets and off-chain model storage
CovFedAvg selects federated models using local low-loss curves
On width-16 gas-sensor clients, balanced accuracy rose from FedAvg's 88.88% to 89.84%, below matched fine-tuning.
Federated deepfake Grad-CAM faithfulness collapses at extreme heterogeneity
An EfficientNet-B4 on FaceForensics++ matches a centralized baseline until client data is extremely non-IID, when explanations turn misleading.
Survey maps security risks in distributed and federated learning
Federated learning is treated as a high-risk case, with defenses compared from aggregation to trusted execution.
Noisy aggregation cannot match central DP for private selection
A proposed Sparse Vector Technique primitive reaches central-model error with O(d log-star d) expected queries.
NVIDIA and C-BRAIN apply AI tools to speed Alzheimer’s research
OpenScientist finished analyses in minutes that scientists said would take weeks to months, at under $10 a run.
1
Distributed log parsers tested across 6,720 federated configurations
Five parsers plus aggregation methods were compared so clients can agree on event templates without ground-truth logs.
Paper formulates split federated unlearning and proposes SURE
SURE uses dual-importance estimation and selective perturbation, matching retraining at modest extra cost.
Federated breast-imaging models may be confounded by acquisition year
Normal-versus-sick ROC-AUC was 0.940-0.990, but year alone scored 0.974 on the same partition.
Secure aggregation scheme supports heterogeneous client quantization in federated learning
It avoids leaking partial aggregates when clients quantize differently and up to T semi-honest clients collude with the server.