Research map / Adversarial robustness and security / Certified and empirical robustness
Lower Bounds on Adversarial Robustness from Optimal Transport
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 |
|---|---|---|---|
| increase l2 adversarial budget beta | robust classifiers vs optimal-transport lower bound · MNIST/Fashion-MNIST/CIFAR-10 3 vs 7 (l2) | minimum 0-1 loss gap | Hurt |
Closest papers by meaning
- Adversarial Risk via Optimal Transport and Optimal Couplings (ICML 2020 · similarity 0.93)
- The Many Faces of Adversarial Risk (NeurIPS 2021 · similarity 0.91)
- Achieving Robustness in Classification Using Optimal Transport With Hinge Regularization (CVPR 2021 · similarity 0.91)
- Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker (NeurIPS 2023 · similarity 0.90)
- Theoretical Analysis of Adversarial Learning: A Minimax Approach (NeurIPS 2019 · similarity 0.90)
- Gradient Flow Provably Learns Robust Classifiers for Orthonormal GMMs (ICML 2025 · similarity 0.87)
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.