AI Paper Atlas

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

SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud

Zahra Ghodsi, Tianyu Gu, Siddharth Garg

NeurIPS 2017 · Federated learning and privacy › Privacy attacks and secure learning · approach: Encryption-based private learning · 90 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
Use quadratic activations instead of ReLUs (ablation)CNN-2-Quad and FcNN-3-Quad · MNIST, MNIST-Back-Rand, and TIMITclassification errorNo clear effect
Increase input and weight scaling factors (ablation)SafetyNets on MNIST-Back-Rand · MNIST-Back-Rand validationerror: 0.188 -> 0.035Improved
Select α=16 and β=16 under the p=2^{61}-1 field limit (ablation)SafetyNets (CNN-2-Quad) · MNIST-Back-Rand testerror: 4.67%Improved
Use the specialized activation proof together with matrix-multiplication proofs rather than verifying each layer separatelySafetyNets · Neural-network inferencebandwidthImproved
Outsource verification using SafetyNets instead of executing FcNN-Quad-3 locallyFcNN-Quad-3 · Batch sizes 256–2048client runtime: 8× to 82×Improved

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