AI Paper Atlas

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

Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information

Kiwan Maeng, Chuan Guo, Sanjay Kariyappa, G. Edward Suh

NeurIPS 2023 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning

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
add dFIL optimizations (compression layer, SNR regularizer) over plain noise (ablation)dFIL split inference · CIFAR-10 ResNet-18 early, 1/dFIL=10accuracy: 10.70% -> 74.44%Improved
add dFIL optimizations over plain noise (ablation)dFIL split inference · CIFAR-10 ResNet-18 middle, 1/dFIL=100accuracy: 12.94% -> 84.27%Improved
add dFIL optimizations over plain noise (ablation)dFIL split inference · MovieLens-20M NCF-MLP, 1/dFIL=100AUC: 0.6120 -> 0.8081Improved
add dFIL optimizations over plain noise, split late (ablation)dFIL split inference · GLUE-SST2 DistilBert, 1/dFIL=10accuracy: 90.25% -> 83.03%Hurt
add dFIL optimizations over plain noise, split late (ablation)dFIL split inference · GLUE-SST2 DistilBert, 1/dFIL=100accuracy: 82.68% -> 82.82%No clear effect
split earlier in the networkdFIL split inference · CIFAR-10 ResNet-18, 1/dFIL=10accuracy: 92.35% -> 74.44%Hurt
increase 1/dFIL from 10 to 100 (less privacy budget of noise)dFIL training on encoded data · CIFAR-10, CIFAR-100 pretrained encoderaccuracy: 80.16% -> 70.27%Hurt
pretrain encoder on held-out CIFAR-10 instead of CIFAR-100dFIL training on encoded data · CIFAR-10, 1/dFIL=100accuracy: 70.27% -> 78.65%Improved
dFIL-based encoder instead of DP-based encoder at same unbiased MSE boundsplit inference · CIFAR-10 ResNet-18, MSE bound 1e-5accuracy: 64.64% -> 93.09%Improved
dFIL-based instead of DP-based encoder at looser bound 1e-2split inference · CIFAR-10 ResNet-18, MSE bound 1e-2accuracy: 33\% -> 87.52%Improved
reduce randomized smoothing noise from 0.25 to 0.01 for score matching (ablation)dFIL bound estimation · MNIST/CIFAR-10bound validityHurt
use arbitrary-attack bound (Bound-ours) instead of unbiased bounddFIL bound · synthetic Gaussian, MNIST, CIFAR-10bound validityImproved

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