Research map / Architectures and efficiency / RNNs and normalization
AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use layer-wise HE parameter selection instead of DELPHI's network-wide selection | HPPNNs · 7CNet, ResNet-32, and MobileNet-V2 | total latency: 53%~70% | Helped |
| Use layer-wise HE parameter selection instead of DARL's network-wide selection | HPPNNs · 7CNet, ResNet-32, and MobileNet-V2 | accuracy: 76.78 -> 76.78 | No clear effect |
| Use layer-wise HE parameter selection instead of DARL's network-wide selection | HPPNNs · 7CNet | accuracy: 81.63 -> 81.5 | Hurt |
| Use layer-wise HE parameter selection instead of DARL's network-wide selection | HPPNNs · MobileNet-V2 | accuracy: 68.08 -> 68.05 | Hurt |
| Add finetuning using generated decryption errors (ablation) | AutoPrivacy-optimized HPPNNs · CIFAR-10 and CIFAR-100 experiments | inference accuracy: 8% | Helped |
| Add finetuning using generated decryption errors (ablation) | AutoPrivacy-optimized ResNet · CIFAR-100 | inference accuracy | Helped |
Closest papers by meaning
- Low Latency Privacy Preserving Inference (ICML 2019 · similarity 0.87)
- SAFENet: A Secure, Accurate and Fast Neural Network Inference (ICLR 2021 · similarity 0.86)
- SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference (ICML 2023 · similarity 0.86)
- United We Stand: Accelerating Privacy-Preserving Neural Inference by Conjunctive Optimization with Interleaved Nexus (AAAI 2024 · similarity 0.84)
- PrivCirNet: Efficient Private Inference via Block Circulant Transformation (NeurIPS 2024 · similarity 0.84)
- Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic (NeurIPS 2026 · similarity 0.84)
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.