AI Paper Atlas

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

Towards Certificated Model Robustness Against Weight Perturbations

Tsui-Wei Weng, Pu Zhao, Sijia Liu, Pin-Yu Chen, Xue Lin, Luca Daniel

AAAI 2020 · Adversarial robustness and security › Certified and empirical robustness · approach: Neural network robustness verification · 38 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
add certification constraint (epsilon at a percentile of certified bounds) to ADMM weight quantization (ablation)8-layer MLP quantized (4/6/8 bits) · SVHNtest accuracy: around 10% improvementImproved
increase certification epsilon from 100th percentile to 10 times that bound (ablation)certified quantization · 6-layer MLP 6-bittest accuracy (%): 83% -> 76.1%Hurt
use proposed ADMM (auxiliary variable on V, includes q) instead of LB method even without certificationADMM quantization · MNIST-Fashion and SVHNtraining accuracyImproved
add certification constraints to the proposed ADMM quantization (ablation)ADMM quantization · MNIST-Fashion and SVHNtraining and test accuracyImproved
choice of epsilon percentile in certification constraint (below 90th percentile) (ablation)certified quantization · SVHN 8-layer MLPtest accuracyNo clear effect

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