AI Paper Atlas

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

Semialgebraic Representation of Monotone Deep Equilibrium Models and Applications to Certification

Tong Chen, Jean B. Lasserre, Victor Magron, Edouard Pauwels

NeurIPS 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Neural network robustness verification · 3 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 Robustness Model instead of Lipschitz Modelcertification · MNIST Linf eps=0.05certified ratio: 0% -> 24%Improved
Use Robustness Model instead of Lipschitz Modelcertification · MNIST Linf eps=0.01certified ratio: 24% -> 99%Improved
Use Ellipsoid Model instead of Lipschitz Modelcertification · MNIST Linf eps=0.01certified ratio: 24% -> 92%Improved
Use Ellipsoid Model instead of Lipschitz Modelcertification · MNIST L2 eps=0.1certified ratio: 91% -> 99%Improved
Use Robustness Model instead of Ellipsoid Modelcertification · MNIST Linf eps=0.05certified ratio: 0% -> 24%Improved
Use Robustness Model instead of Ellipsoid Modelcertification · MNIST Linf eps=0.01certified ratio: 92% -> 99%Improved
Use Robustness Model instead of Ellipsoid Modelrunning time per example · MNISTseconds: 500s -> 1350sHurt
Use Lipschitz Model's directly computed constant instead of bound from [33]Lipschitz upper bound · q=2bound: 4.80 -> 4.67Improved
Use Lipschitz Model's directly computed constant instead of bound from [33]Lipschitz upper bound · q=infbound: 824.14 -> 108.84Improved
Use Lipschitz Model's directly computed constant instead of bound from [33]certification · MNIST Linf eps=0.01certified ratio: 0% -> 24%Improved
Use Lipschitz Model instead of bound from [33]computation time · Lipschitz bound q=infseconds: 1898.65Hurt
Increase perturbation eps from 0.01 to 0.1Robustness Model · MNIST Linfcertified ratio: 99% -> 0%Hurt

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