Research map / Adversarial robustness and security / Certified and empirical robustness
Theoretical Analysis of Adversarial Learning: A Minimax Approach
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 |
|---|---|---|---|
| Use the weak Lipschitz condition and data-dependent range for the dual parameter instead of a fixed Lipschitz range | Minimax adversarial risk bound · Adversarial learning | risk-bound tightness | Helped |
| Set the adversary radius to zero | Minimax adversarial risk bound · Non-adversarial learning | risk bound | Helped |
| Increase the adversary radius when ε_B ≥ M/λ⁺_{f,P_n} | Minimax adversarial risk bound · Adversarial learning | extra complexity term | Helped |
Closest papers by meaning
- Lower Bounds on Adversarial Robustness from Optimal Transport (NeurIPS 2019 · similarity 0.90)
- Sharp Statistical Guaratees for Adversarially Robust Gaussian Classification (ICML 2020 · similarity 0.90)
- Adversarial Multiclass Classification: A Risk Minimization Perspective (NeurIPS 2016 · similarity 0.90)
- Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization (NeurIPS 2022 · similarity 0.90)
- On the Generalization Analysis of Adversarial Learning (ICML 2022 · similarity 0.90)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · similarity 0.88)
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.