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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use quadratic activations instead of ReLUs (ablation) | CNN-2-Quad and FcNN-3-Quad · MNIST, MNIST-Back-Rand, and TIMIT | classification error | No clear effect |
| Increase input and weight scaling factors (ablation) | SafetyNets on MNIST-Back-Rand · MNIST-Back-Rand validation | error: 0.188 -> 0.035 | Improved |
| Select α=16 and β=16 under the p=2^{61}-1 field limit (ablation) | SafetyNets (CNN-2-Quad) · MNIST-Back-Rand test | error: 4.67% | Improved |
| Use the specialized activation proof together with matrix-multiplication proofs rather than verifying each layer separately | SafetyNets · Neural-network inference | bandwidth | Improved |
| Outsource verification using SafetyNets instead of executing FcNN-Quad-3 locally | FcNN-Quad-3 · Batch sizes 256–2048 | client runtime: 8× to 82× | Improved |
Closest papers by meaning
- Towards Trustworthy Deep Learning (AAAI 2024 · similarity 0.87)
- Certified but Private: Scalable Zero-Knowledge Proofs for the Formal Verification of Neural Networks (NeurIPS 2026 · similarity 0.87)
- No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks (ICML 2025 · similarity 0.85)
- TensorCommitments: A Lightweight Verifiable Inference for Large Language Models (NeurIPS 2026 · similarity 0.85)
- VNN: Verification-Friendly Neural Networks with Hard Robustness Guarantees (ICML 2024 · similarity 0.85)
- FairProof : Confidential and Certifiable Fairness for Neural Networks (ICML 2024 · similarity 0.85)
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.
