AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Quantization-Aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks

Mathias Lechner, Đorđe Žikelić, Krishnendu Chatterjee, Thomas A. Henzinger, Daniela Rus

AAAI 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Neural network robustness verification · 4 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
Train quantized networks with QA-IBP rather than prior QF_BV SMT-certified modelsQNNs · MNIST and Fashion-MNIST at ε=0, 1, and 4certified robust accuracy: 99.2% vs 97.1%; 98.8% vs 92%; 95.6% vs 53%; 86.3% vs 85.6%; 80.0% vs 76%; 59.8% vs 36%Improved
Use QA-IBP instead of the strongest prior QF_BV SMT resultQNNs · MNIST ε=1certified robust accuracy: 99% vs 98.8%Hurt
Add branching into subdomains to IBP bounds plus PGD (ablation)QA-IBP verifier · MNIST ε=4undetermined samples: 3.51% -> 3.47%Improved
Add branching into subdomains to IBP bounds plus PGD (ablation)QA-IBP verifier · Fashion-MNIST ε=1 and ε=4undetermined samples: 3.96% -> 3.93%; 19.23% -> 18.51%Improved
Add branching into subdomains to IBP bounds plus PGD (ablation)QA-IBP verifier · MNIST ε=1undetermined samples: 0.35% -> 0.35%No clear effect
Reduce weight decay from 1·10^-4 to 1·10^-5 (ablation)QA-IBP CIFAR-10 model · CIFAR-10 ε=0 versus ε=1 and ε=4certified robust accuracy: 30.0% -> 83.1%; 28.4% -> 0%; 22.4% -> 0%Mixed
Use weight decay 5·10^-5 instead of 1·10^-4 (ablation)QA-IBP CIFAR-10 model · CIFAR-10 ε=0 and ε=1 versus ε=4certified robust accuracy: 30.0% -> 39.6%; 28.4% -> 34.1%; 22.4% -> 20.6%Mixed

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