GPU CKKS path speeds encrypted MNIST training about 49 times
In a matched 100-update run, device-resident bootstrapping cut training from 14,268.295 to 293.075 seconds with equal decoded parameters.
Stories per day · 30 days
1 RSS
Relatedckks1federated-learning1gpu1homomorphic-encryption1label-flipping1rust1semi-decentralized1trust1
8 stories, newest first · one card per story
Stories tagged #mnist
Paper screens federated updates against label-flipping attacks
On 50 MNIST clients, screening rejected most malicious updates while keeping most benign ones.
Toward Joint Optimization of Circuit Depth and Training Data Size in Adaptively Grown Quantum Classifiers
Reimplemented Q-FLAIR finds no reliable link between MNIST training-set size and grown quantum circuit depth.
Feature Selective Model Collapse in Diffusion Models: Total Replacement versus Fixed-Budget Training
Fixed-budget diffusion retraining loses only fragile features, unlike full replacement with synthetic data.
Data Unlearning via Inverse Distillation
Inverse Distillation Unlearning distills diffusion and flow models into one-step generators while suppressing a designated forget set.
Common-Mode Collapse and Recovery in Direct Feedback Alignment
Direct feedback alignment can stall when a shared error mode saturates tanh hidden units.
Learning Holographic Reduced Representations with Clifford Variational Autoencoders
Clifford-VAE learns torus embeddings that beat Gaussian VAEs on vector-symbolic binding and capacity tests.
End-to-End Hard-Label Cryptanalytic Model Extraction Using Efficient Sign Recovery
Researchers show end-to-end hard-label extraction of small ReLU MLPs, exceeding 98% label agreement on MNIST.