Research map / Adversarial robustness and security / Certified and empirical robustness
Invariant Representations through Adversarial Forgetting
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 adversarial forgetting instead of UAI | Invariant Representations through Adversarial Forgetting · Chairs | A_y: 0.74 -> 0.84 | Helped |
| use adversarial forgetting instead of UAI | Invariant Representations through Adversarial Forgetting · Chairs | A_s: 0.34 -> 0.25 | Helped |
| use adversarial forgetting instead of UAI | Invariant Representations through Adversarial Forgetting · Extended Yale-B | A_y: 0.95 -> 0.95 | No clear effect |
| use adversarial forgetting instead of UAI | Invariant Representations through Adversarial Forgetting · Extended Yale-B | A_s: 0.24 -> 0.20 | Helped |
| use adversarial forgetting instead of UAI | Invariant Representations through Adversarial Forgetting · MNIST-ROT | A_y: 0.977 -> 0.991; 0.856 -> 0.863; 0.696 -> 0.730 | Helped |
| use adversarial forgetting instead of UAI | Invariant Representations through Adversarial Forgetting · MNIST-ROT, Θ | A_s: 0.338 -> 0.201 | Helped |
| use adversarial forgetting instead of VFAE | Invariant Representations through Adversarial Forgetting · Adult | A_y: 0.76 -> 0.85 | Helped |
| use adversarial forgetting instead of VFAE | Invariant Representations through Adversarial Forgetting · Adult | A_s: 0.67 -> 0.67 | No clear effect |
| use adversarial forgetting instead of NN+MMD | Invariant Representations through Adversarial Forgetting · German | A_y: 0.74 -> 0.76 | Helped |
| use adversarial forgetting instead of NN+MMD | Invariant Representations through Adversarial Forgetting · German | A_s: 0.80 -> 0.80 | No clear effect |
| remove decoder, maskers, and discriminators and predict directly from z (ablation) | Multi-task adversarial forgetting · dSprites task #1 | A_s: 0.50 -> 0.94 | Hurt |
| remove decoder, maskers, and discriminators and predict directly from z (ablation) | Multi-task adversarial forgetting · dSprites task #2 | A_s: 0.25 -> 0.40 | Hurt |
Closest papers by meaning
- Invariant Representations without Adversarial Training (NeurIPS 2018 · similarity 0.90)
- Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness (ICLR 2025 · similarity 0.89)
- Unsupervised Adversarial Invariance (NeurIPS 2018 · similarity 0.89)
- The Effectiveness of Random Forgetting for Robust Generalization (ICLR 2024 · similarity 0.87)
- Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off (ICLR 2025 · similarity 0.86)
- Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting (AAAI 2025 · similarity 0.85)
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.