AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data

Qian Lou, Bo Feng, Geoffrey Charles Fox, Lei Jiang

NeurIPS 2020 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace BGV lookup-table sigmoid activations with TFHE ReLU/softmax and switch between BGV and TFHE (ablation)FHESGD-based MLP · Encrypted MNISTmini-batch training latency: reduces latency by 97.4%Improved
Use BGV instead of BFV for linear layers in the switching scheme (ablation)Glyph MLP · Encrypted MNISTmini-batch training latency: 76.4% decrease vs ChimeraImproved
Use CNN with transfer learning (fixed SVHN-pretrained conv layers) instead of MLP (ablation)Glyph · Encrypted MNISTtraining latency: 56.7% decreaseImproved
Use CNN with transfer learning instead of MLP (ablation)Glyph · Encrypted MNISTtest accuracy: ~2%Improved
Add transfer learning (SVHN features) to Glyph CNN (ablation)Glyph CNN · MNIST after 5 epochstest accuracy (%): 97.1 -> 98.6Improved
Add transfer learning (CIFAR-10 features) to Glyph CNN (ablation)Glyph CNN · Skin-Cancer-MNISTtest accuracy: +4% test accuracy boostImproved
Use CNN architecture instead of FHESGD MLP without transfer learning (ablation)Glyph CNN · MNIST after 5 epochstest accuracy (%): 96.4 -> 97.1Improved
Use BGV-TFHE Glyph CNN instead of BFV-TFHE Chimera CNNGlyph · Encrypted MNISTtraining latency: 69% reduction; 28.6 days -> 8 daysImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy