Research map / Adversarial robustness and security / Certified and empirical robustness
Learning to Pivot with Adversarial Networks
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 |
|---|---|---|---|
| Add adversarial pivotality training with λ=10 | W-jet classifier · W-jet classification test | AMS: 7 -> around 7.8 | Helped |
| Increase the pivotality trade-off parameter from λ=10 to λ=500 (ablation) | Adversarial pivot classifier · W-jet classification test | AMS | Hurt |
| Add adversarial training against the continuous nuisance Z | Toy classifier · Continuous-nuisance Gaussian toy example | Dependence of decision-score distributions on Z | Helped |
| Trade classification accuracy for independence from pileup using λ=10 | W-jet classifier · W-jet classification test | AMS: 7 -> around 7.8 | Helped |
Closest papers by meaning
- Attribute-Guided Adversarial Training for Robustness to Natural Perturbations (AAAI 2021 · similarity 0.86)
- Certifying Some Distributional Robustness with Principled Adversarial Training (ICLR 2018 · similarity 0.86)
- Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation (AAAI 2024 · similarity 0.85)
- Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment (ICML 2019 · similarity 0.85)
- Improving Calibration through the Relationship with Adversarial Robustness (NeurIPS 2021 · similarity 0.85)
- Learning Better Certified Models from Empirically-Robust Teachers (NeurIPS 2026 · similarity 0.84)
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.